https://www.spreaker.com/podcast/zundamon-nohugging-facenyusu--6849834jaTechnologyksterxhttps://d3wo5wojvuv7l.cloudfront.net/t_rss_itunes_square_1400/images.spreaker.com/original/f367fc1b79489f53e55def91a2d48116.jpghttps://www.spreaker.com/podcast/zundamon-nohugging-facenyusu--6849834Fri, 17 Jul 2026 22:55:30 +0000ksterxksterxkostonerx@gmail.comHugging Face Trending Papersの要約を毎日日本語で配信。falseepisodichttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-18--730354611. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
https://huggingface.co/papers/2607.14935
2. SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
https://huggingface.co/papers/2607.14777
3. SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
https://huggingface.co/papers/2607.15257
4. LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
https://huggingface.co/papers/2607.14952
5. BadWAM: When World-Action Models Dream Right but Act Wrong
https://huggingface.co/papers/2607.15207]]>https://api.spreaker.com/episode/73035461Fri, 17 Jul 2026 22:55:01 +0000ksterx【本日の論文】 1. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding https://huggingface.co/papers/2607.14935 2. SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning...1. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
https://huggingface.co/papers/2607.14935
2. SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
https://huggingface.co/papers/2607.14777
3. SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
https://huggingface.co/papers/2607.15257
4. LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
https://huggingface.co/papers/2607.14952
5. BadWAM: When World-Action Models Dream Right but Act Wrong
https://huggingface.co/papers/2607.15207]]>197ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-17--730197261. Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
https://huggingface.co/papers/2607.13285
2. Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation
https://huggingface.co/papers/2607.13125
3. Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
https://huggingface.co/papers/2607.12395
4. KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
https://huggingface.co/papers/2607.12625
5. OvisOCR2 Technical Report
https://huggingface.co/papers/2607.13639]]>https://api.spreaker.com/episode/73019726Thu, 16 Jul 2026 23:01:18 +0000ksterx【本日の論文】 1. Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable https://huggingface.co/papers/2607.13285 2. Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation...1. Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
https://huggingface.co/papers/2607.13285
2. Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation
https://huggingface.co/papers/2607.13125
3. Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
https://huggingface.co/papers/2607.12395
4. KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
https://huggingface.co/papers/2607.12625
5. OvisOCR2 Technical Report
https://huggingface.co/papers/2607.13639]]>194ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-16--730034191. SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding
https://huggingface.co/papers/2607.10400
2. Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
https://huggingface.co/papers/2607.11886
3. Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
https://huggingface.co/papers/2607.05382
4. Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
https://huggingface.co/papers/2607.08317
5. Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
https://huggingface.co/papers/2607.12463]]>https://api.spreaker.com/episode/73003419Wed, 15 Jul 2026 23:02:58 +0000ksterx【本日の論文】 1. SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding https://huggingface.co/papers/2607.10400 2. Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation...1. SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding
https://huggingface.co/papers/2607.10400
2. Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
https://huggingface.co/papers/2607.11886
3. Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
https://huggingface.co/papers/2607.05382
4. Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
https://huggingface.co/papers/2607.08317
5. Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
https://huggingface.co/papers/2607.12463]]>196ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-15--729791671. Weak-to-Strong Generalization via Direct On-Policy Distillation
https://huggingface.co/papers/2607.05394
2. ABot-N1: Toward a General Visual Language Navigation Foundation Model
https://huggingface.co/papers/2607.10383
3. ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
https://huggingface.co/papers/2607.10350
4. 4D Human-Scene Reconstruction from Low-Overlap Captures
https://huggingface.co/papers/2607.09125
5. LightMem-Ego: Your AI Memory for Everyday Life
https://huggingface.co/papers/2607.11487]]>https://api.spreaker.com/episode/72979167Tue, 14 Jul 2026 23:03:24 +0000ksterx【本日の論文】 1. Weak-to-Strong Generalization via Direct On-Policy Distillation https://huggingface.co/papers/2607.05394 2. ABot-N1: Toward a General Visual Language Navigation Foundation Model https://huggingface.co/papers/2607.10383 3....1. Weak-to-Strong Generalization via Direct On-Policy Distillation
https://huggingface.co/papers/2607.05394
2. ABot-N1: Toward a General Visual Language Navigation Foundation Model
https://huggingface.co/papers/2607.10383
3. ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
https://huggingface.co/papers/2607.10350
4. 4D Human-Scene Reconstruction from Low-Overlap Captures
https://huggingface.co/papers/2607.09125
5. LightMem-Ego: Your AI Memory for Everyday Life
https://huggingface.co/papers/2607.11487]]>256ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-14--729569991. Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
https://huggingface.co/papers/2607.08964
2. Scalable Visual Pretraining for Language Intelligence
https://huggingface.co/papers/2607.09657
3. Video Generation Models are General-Purpose Vision Learners
https://huggingface.co/papers/2607.09024
4. Trust Region Policy Distillation
https://huggingface.co/papers/2607.04751
5. KronQ: LLM Quantization via Kronecker-Factored Hessian
https://huggingface.co/papers/2607.07964]]>https://api.spreaker.com/episode/72956999Mon, 13 Jul 2026 23:00:39 +0000ksterx【本日の論文】 1. Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading https://huggingface.co/papers/2607.08964 2. Scalable Visual Pretraining for Language Intelligence...1. Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
https://huggingface.co/papers/2607.08964
2. Scalable Visual Pretraining for Language Intelligence
https://huggingface.co/papers/2607.09657
3. Video Generation Models are General-Purpose Vision Learners
https://huggingface.co/papers/2607.09024
4. Trust Region Policy Distillation
https://huggingface.co/papers/2607.04751
5. KronQ: LLM Quantization via Kronecker-Factored Hessian
https://huggingface.co/papers/2607.07964]]>199ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-13--729426121. Vidu S1: A Real-Time Interactive Video Generation Model
https://huggingface.co/papers/2607.03118
2. Video-Oasis: Rethinking Evaluation of Video Understanding
https://huggingface.co/papers/2603.29616
3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
https://huggingface.co/papers/2601.16211
4. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
https://huggingface.co/papers/2607.08758
5. LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
https://huggingface.co/papers/2607.08770]]>https://api.spreaker.com/episode/72942612Sun, 12 Jul 2026 22:53:44 +0000ksterx【本日の論文】 1. Vidu S1: A Real-Time Interactive Video Generation Model https://huggingface.co/papers/2607.03118 2. Video-Oasis: Rethinking Evaluation of Video Understanding https://huggingface.co/papers/2603.29616 3. Why Can't I Open My Drawer?...1. Vidu S1: A Real-Time Interactive Video Generation Model
https://huggingface.co/papers/2607.03118
2. Video-Oasis: Rethinking Evaluation of Video Understanding
https://huggingface.co/papers/2603.29616
3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
https://huggingface.co/papers/2601.16211
4. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
https://huggingface.co/papers/2607.08758
5. LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
https://huggingface.co/papers/2607.08770]]>227ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-12--729337091. Vidu S1: A Real-Time Interactive Video Generation Model
https://huggingface.co/papers/2607.03118
2. Video-Oasis: Rethinking Evaluation of Video Understanding
https://huggingface.co/papers/2603.29616
3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
https://huggingface.co/papers/2601.16211
4. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
https://huggingface.co/papers/2607.08758
5. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
https://huggingface.co/papers/2607.08768]]>https://api.spreaker.com/episode/72933709Sat, 11 Jul 2026 22:53:05 +0000ksterx【本日の論文】 1. Vidu S1: A Real-Time Interactive Video Generation Model https://huggingface.co/papers/2607.03118 2. Video-Oasis: Rethinking Evaluation of Video Understanding https://huggingface.co/papers/2603.29616 3. Why Can't I Open My Drawer?...1. Vidu S1: A Real-Time Interactive Video Generation Model
https://huggingface.co/papers/2607.03118
2. Video-Oasis: Rethinking Evaluation of Video Understanding
https://huggingface.co/papers/2603.29616
3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
https://huggingface.co/papers/2601.16211
4. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
https://huggingface.co/papers/2607.08758
5. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
https://huggingface.co/papers/2607.08768]]>238ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-11--729217011. Vidu S1: A Real-Time Interactive Video Generation Model
https://huggingface.co/papers/2607.03118
2. Video-Oasis: Rethinking Evaluation of Video Understanding
https://huggingface.co/papers/2603.29616
3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
https://huggingface.co/papers/2601.16211
4. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
https://huggingface.co/papers/2607.08768
5. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
https://huggingface.co/papers/2607.08758]]>https://api.spreaker.com/episode/72921701Fri, 10 Jul 2026 23:04:27 +0000ksterx【本日の論文】 1. Vidu S1: A Real-Time Interactive Video Generation Model https://huggingface.co/papers/2607.03118 2. Video-Oasis: Rethinking Evaluation of Video Understanding https://huggingface.co/papers/2603.29616 3. Why Can't I Open My Drawer?...1. Vidu S1: A Real-Time Interactive Video Generation Model
https://huggingface.co/papers/2607.03118
2. Video-Oasis: Rethinking Evaluation of Video Understanding
https://huggingface.co/papers/2603.29616
3. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
https://huggingface.co/papers/2601.16211
4. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
https://huggingface.co/papers/2607.08768
5. Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
https://huggingface.co/papers/2607.08758]]>184ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-10--729010681. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
https://huggingface.co/papers/2607.07708
2. Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
https://huggingface.co/papers/2607.07608
3. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
https://huggingface.co/papers/2607.07675
4. Infinite Worlds with Versatile Interactions
https://huggingface.co/papers/2607.07534
5. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
https://huggingface.co/papers/2607.07508]]>https://api.spreaker.com/episode/72901068Thu, 09 Jul 2026 23:16:25 +0000ksterx【本日の論文】 1. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning https://huggingface.co/papers/2607.07708 2. Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation...1. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
https://huggingface.co/papers/2607.07708
2. Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
https://huggingface.co/papers/2607.07608
3. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
https://huggingface.co/papers/2607.07675
4. Infinite Worlds with Versatile Interactions
https://huggingface.co/papers/2607.07534
5. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
https://huggingface.co/papers/2607.07508]]>198ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-09--728770581. RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
https://huggingface.co/papers/2607.06559
2. AlayaWorld: Long-Horizon and Playable Video World Generation
https://huggingface.co/papers/2607.06291
3. RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
https://huggingface.co/papers/2607.06558
4. Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
https://huggingface.co/papers/2607.02980
5. Vision as Unified Multimodal Generation
https://huggingface.co/papers/2607.06560]]>https://api.spreaker.com/episode/72877058Wed, 08 Jul 2026 23:13:32 +0000ksterx【本日の論文】 1. RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation https://huggingface.co/papers/2607.06559 2. AlayaWorld: Long-Horizon and Playable Video World Generation https://huggingface.co/papers/2607.06291 3. RynnWorld-Teleop: An...1. RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
https://huggingface.co/papers/2607.06559
2. AlayaWorld: Long-Horizon and Playable Video World Generation
https://huggingface.co/papers/2607.06291
3. RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
https://huggingface.co/papers/2607.06558
4. Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
https://huggingface.co/papers/2607.02980
5. Vision as Unified Multimodal Generation
https://huggingface.co/papers/2607.06560]]>254ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-08--728600571. OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
https://huggingface.co/papers/2607.04033
2. UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
https://huggingface.co/papers/2607.04425
3. ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
https://huggingface.co/papers/2607.04438
4. PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
https://huggingface.co/papers/2607.05373
5. ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
https://huggingface.co/papers/2607.04439]]>https://api.spreaker.com/episode/72860057Tue, 07 Jul 2026 23:05:56 +0000ksterx【本日の論文】 1. OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers https://huggingface.co/papers/2607.04033 2. UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning https://huggingface.co/papers/2607.04425 3....1. OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
https://huggingface.co/papers/2607.04033
2. UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
https://huggingface.co/papers/2607.04425
3. ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
https://huggingface.co/papers/2607.04438
4. PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
https://huggingface.co/papers/2607.05373
5. ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
https://huggingface.co/papers/2607.04439]]>257ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-07--728456871. The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
https://huggingface.co/papers/2606.29526
2. Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
https://huggingface.co/papers/2607.02501
3. OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
https://huggingface.co/papers/2607.02461
4. VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
https://huggingface.co/papers/2607.01804
5. DataComp-VLM: Improved Open Datasets for Vision-Language Models
https://huggingface.co/papers/2606.28551]]>https://api.spreaker.com/episode/72845687Mon, 06 Jul 2026 23:12:20 +0000ksterx【本日の論文】 1. The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning https://huggingface.co/papers/2606.29526 2. Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on...1. The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
https://huggingface.co/papers/2606.29526
2. Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
https://huggingface.co/papers/2607.02501
3. OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
https://huggingface.co/papers/2607.02461
4. VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
https://huggingface.co/papers/2607.01804
5. DataComp-VLM: Improved Open Datasets for Vision-Language Models
https://huggingface.co/papers/2606.28551]]>168ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-06--728328131. Program-as-Weights: A Programming Paradigm for Fuzzy Functions
https://huggingface.co/papers/2607.02512
2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
https://huggingface.co/papers/2607.02255
3. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
https://huggingface.co/papers/2607.02440
4. Morphing into Hybrid Attention Models
https://huggingface.co/papers/2606.30562
5. Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
https://huggingface.co/papers/2607.01642]]>https://api.spreaker.com/episode/72832813Sun, 05 Jul 2026 23:06:37 +0000ksterx【本日の論文】 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://huggingface.co/papers/2607.02512 2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents https://huggingface.co/papers/2607.02255 3. EvoPolicyGym:...1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions
https://huggingface.co/papers/2607.02512
2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
https://huggingface.co/papers/2607.02255
3. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
https://huggingface.co/papers/2607.02440
4. Morphing into Hybrid Attention Models
https://huggingface.co/papers/2606.30562
5. Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
https://huggingface.co/papers/2607.01642]]>219ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-05--728227361. Program-as-Weights: A Programming Paradigm for Fuzzy Functions
https://huggingface.co/papers/2607.02512
2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
https://huggingface.co/papers/2607.02255
3. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
https://huggingface.co/papers/2607.02440
4. Morphing into Hybrid Attention Models
https://huggingface.co/papers/2606.30562
5. Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
https://huggingface.co/papers/2607.01642]]>https://api.spreaker.com/episode/72822736Sat, 04 Jul 2026 23:03:38 +0000ksterx【本日の論文】 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://huggingface.co/papers/2607.02512 2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents https://huggingface.co/papers/2607.02255 3. EvoPolicyGym:...1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions
https://huggingface.co/papers/2607.02512
2. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
https://huggingface.co/papers/2607.02255
3. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
https://huggingface.co/papers/2607.02440
4. Morphing into Hybrid Attention Models
https://huggingface.co/papers/2606.30562
5. Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
https://huggingface.co/papers/2607.01642]]>183ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-04--728118621. Program-as-Weights: A Programming Paradigm for Fuzzy Functions
https://huggingface.co/papers/2607.02512
2. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
https://huggingface.co/papers/2607.02440
3. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
https://huggingface.co/papers/2607.02255
4. Morphing into Hybrid Attention Models
https://huggingface.co/papers/2606.30562
5. Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
https://huggingface.co/papers/2607.01642]]>https://api.spreaker.com/episode/72811862Fri, 03 Jul 2026 23:08:51 +0000ksterx【本日の論文】 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://huggingface.co/papers/2607.02512 2. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments https://huggingface.co/papers/2607.02440 3....1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions
https://huggingface.co/papers/2607.02512
2. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
https://huggingface.co/papers/2607.02440
3. AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
https://huggingface.co/papers/2607.02255
4. Morphing into Hybrid Attention Models
https://huggingface.co/papers/2606.30562
5. Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
https://huggingface.co/papers/2607.01642]]>235ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-03--727963871. PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
https://huggingface.co/papers/2606.28322
2. ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
https://huggingface.co/papers/2607.00466
3. TurboServe: Serving Streaming Video Generation Efficiently and Economically
https://huggingface.co/papers/2606.19271
4. MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
https://huggingface.co/papers/2607.01071
5. Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
https://huggingface.co/papers/2607.00461]]>https://api.spreaker.com/episode/72796387Thu, 02 Jul 2026 23:12:49 +0000ksterx【本日の論文】 1. PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception https://huggingface.co/papers/2606.28322 2. ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving https://huggingface.co/papers/2607.00466...1. PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
https://huggingface.co/papers/2606.28322
2. ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
https://huggingface.co/papers/2607.00466
3. TurboServe: Serving Streaming Video Generation Efficiently and Economically
https://huggingface.co/papers/2606.19271
4. MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
https://huggingface.co/papers/2607.01071
5. Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
https://huggingface.co/papers/2607.00461]]>206ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-07-02--727801451. Orca: The World is in Your Mind
https://huggingface.co/papers/2606.30534
2. Dockerless: Environment-Free Program Verifier for Coding Agents
https://huggingface.co/papers/2606.28436
3. DOPD: Dual On-policy Distillation
https://huggingface.co/papers/2606.30626
4. BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
https://huggingface.co/papers/2606.31315
5. Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
https://huggingface.co/papers/2606.19297]]>https://api.spreaker.com/episode/72780145Wed, 01 Jul 2026 23:21:13 +0000ksterx【本日の論文】 1. Orca: The World is in Your Mind https://huggingface.co/papers/2606.30534 2. Dockerless: Environment-Free Program Verifier for Coding Agents https://huggingface.co/papers/2606.28436 3. DOPD: Dual On-policy Distillation...1. Orca: The World is in Your Mind
https://huggingface.co/papers/2606.30534
2. Dockerless: Environment-Free Program Verifier for Coding Agents
https://huggingface.co/papers/2606.28436
3. DOPD: Dual On-policy Distillation
https://huggingface.co/papers/2606.30626
4. BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
https://huggingface.co/papers/2606.31315
5. Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
https://huggingface.co/papers/2606.19297]]>257ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-18--725712041. LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
https://huggingface.co/papers/2606.18023
2. Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
https://huggingface.co/papers/2606.18216
3. ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
https://huggingface.co/papers/2606.17200
4. GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
https://huggingface.co/papers/2606.17861
5. LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching
https://huggingface.co/papers/2606.16428]]>https://api.spreaker.com/episode/72571204Wed, 17 Jun 2026 23:31:09 +0000ksterx【本日の論文】 1. LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling https://huggingface.co/papers/2606.18023 2. Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients https://huggingface.co/papers/2606.18216 3....1. LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
https://huggingface.co/papers/2606.18023
2. Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
https://huggingface.co/papers/2606.18216
3. ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
https://huggingface.co/papers/2606.17200
4. GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
https://huggingface.co/papers/2606.17861
5. LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching
https://huggingface.co/papers/2606.16428]]>273ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-17--725571191. JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
https://huggingface.co/papers/2606.14777
2. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
https://huggingface.co/papers/2606.11176
3. Geometric Action Model for Robot Policy Learning
https://huggingface.co/papers/2606.17046
4. DreamX-World 1.0: A General-Purpose Interactive World Model
https://huggingface.co/papers/2606.16993
5. FastContext: Training Efficient Repository Explorer for Coding Agents
https://huggingface.co/papers/2606.14066]]>https://api.spreaker.com/episode/72557119Tue, 16 Jun 2026 23:29:44 +0000ksterx【本日の論文】 1. JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence https://huggingface.co/papers/2606.14777 2. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories https://huggingface.co/papers/2606.11176...1. JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
https://huggingface.co/papers/2606.14777
2. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
https://huggingface.co/papers/2606.11176
3. Geometric Action Model for Robot Policy Learning
https://huggingface.co/papers/2606.17046
4. DreamX-World 1.0: A General-Purpose Interactive World Model
https://huggingface.co/papers/2606.16993
5. FastContext: Training Efficient Repository Explorer for Coding Agents
https://huggingface.co/papers/2606.14066]]>220ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-16--725423711. OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
https://huggingface.co/papers/2606.13432
2. APPO: Agentic Procedural Policy Optimization
https://huggingface.co/papers/2606.12384
3. Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
https://huggingface.co/papers/2606.06036
4. From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
https://huggingface.co/papers/2606.14502
5. Orchestra-o1: Omnimodal Agent Orchestration
https://huggingface.co/papers/2606.13707]]>https://api.spreaker.com/episode/72542371Mon, 15 Jun 2026 23:50:12 +0000ksterx【本日の論文】 1. OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data https://huggingface.co/papers/2606.13432 2. APPO: Agentic Procedural Policy Optimization https://huggingface.co/papers/2606.12384 3. Memory is Reconstructed,...1. OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
https://huggingface.co/papers/2606.13432
2. APPO: Agentic Procedural Policy Optimization
https://huggingface.co/papers/2606.12384
3. Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
https://huggingface.co/papers/2606.06036
4. From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
https://huggingface.co/papers/2606.14502
5. Orchestra-o1: Omnimodal Agent Orchestration
https://huggingface.co/papers/2606.13707]]>156ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-15--725272551. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
https://huggingface.co/papers/2606.13681
2. MiniMax Sparse Attention
https://huggingface.co/papers/2606.13392
3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
https://huggingface.co/papers/2606.09426
4. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
https://huggingface.co/papers/2606.13673
5. InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://huggingface.co/papers/2606.13679]]>https://api.spreaker.com/episode/72527255Sun, 14 Jun 2026 23:15:08 +0000ksterx【本日の論文】 1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://huggingface.co/papers/2606.13681 2. MiniMax Sparse Attention https://huggingface.co/papers/2606.13392 3. WeaveBench: A Long-Horizon, Real-World...1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
https://huggingface.co/papers/2606.13681
2. MiniMax Sparse Attention
https://huggingface.co/papers/2606.13392
3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
https://huggingface.co/papers/2606.09426
4. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
https://huggingface.co/papers/2606.13673
5. InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://huggingface.co/papers/2606.13679]]>259ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-14--725164171. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
https://huggingface.co/papers/2606.13681
2. MiniMax Sparse Attention
https://huggingface.co/papers/2606.13392
3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
https://huggingface.co/papers/2606.09426
4. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
https://huggingface.co/papers/2606.13673
5. InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://huggingface.co/papers/2606.13679]]>https://api.spreaker.com/episode/72516417Sat, 13 Jun 2026 23:09:17 +0000ksterx【本日の論文】 1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://huggingface.co/papers/2606.13681 2. MiniMax Sparse Attention https://huggingface.co/papers/2606.13392 3. WeaveBench: A Long-Horizon, Real-World...1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
https://huggingface.co/papers/2606.13681
2. MiniMax Sparse Attention
https://huggingface.co/papers/2606.13392
3. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
https://huggingface.co/papers/2606.09426
4. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
https://huggingface.co/papers/2606.13673
5. InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://huggingface.co/papers/2606.13679]]>204ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-13--725067241. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
https://huggingface.co/papers/2606.13681
2. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
https://huggingface.co/papers/2606.13673
3. MiniMax Sparse Attention
https://huggingface.co/papers/2606.13392
4. InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://huggingface.co/papers/2606.13679
5. Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
https://huggingface.co/papers/2606.08063]]>https://api.spreaker.com/episode/72506724Fri, 12 Jun 2026 23:22:04 +0000ksterx【本日の論文】 1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://huggingface.co/papers/2606.13681 2. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning...1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
https://huggingface.co/papers/2606.13681
2. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
https://huggingface.co/papers/2606.13673
3. MiniMax Sparse Attention
https://huggingface.co/papers/2606.13392
4. InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://huggingface.co/papers/2606.13679
5. Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
https://huggingface.co/papers/2606.08063]]>163ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-12--724901731. Redesign Mixture-of-Experts Routers with Manifold Power Iteration
https://huggingface.co/papers/2606.12397
2. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
https://huggingface.co/papers/2606.11926
3. Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
https://huggingface.co/papers/2606.12191
4. Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
https://huggingface.co/papers/2606.12344
5. Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
https://huggingface.co/papers/2606.09076]]>https://api.spreaker.com/episode/72490173Thu, 11 Jun 2026 23:25:55 +0000ksterx【本日の論文】 1. Redesign Mixture-of-Experts Routers with Manifold Power Iteration https://huggingface.co/papers/2606.12397 2. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement https://huggingface.co/papers/2606.11926 3. Agentic...1. Redesign Mixture-of-Experts Routers with Manifold Power Iteration
https://huggingface.co/papers/2606.12397
2. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
https://huggingface.co/papers/2606.11926
3. Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
https://huggingface.co/papers/2606.12191
4. Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
https://huggingface.co/papers/2606.12344
5. Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
https://huggingface.co/papers/2606.09076]]>221ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-11--724683851. ABot-Earth 0.5: Generative 3D Earth Model
https://huggingface.co/papers/2606.09967
2. Kwai Keye-VL-2.0 Technical Report
https://huggingface.co/papers/2606.10651
3. Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
https://huggingface.co/papers/2606.10917
4. Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
https://huggingface.co/papers/2606.05922
5. SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
https://huggingface.co/papers/2606.09730]]>https://api.spreaker.com/episode/72468385Wed, 10 Jun 2026 23:29:23 +0000ksterx【本日の論文】 1. ABot-Earth 0.5: Generative 3D Earth Model https://huggingface.co/papers/2606.09967 2. Kwai Keye-VL-2.0 Technical Report https://huggingface.co/papers/2606.10651 3. Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution...1. ABot-Earth 0.5: Generative 3D Earth Model
https://huggingface.co/papers/2606.09967
2. Kwai Keye-VL-2.0 Technical Report
https://huggingface.co/papers/2606.10651
3. Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
https://huggingface.co/papers/2606.10917
4. Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
https://huggingface.co/papers/2606.05922
5. SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
https://huggingface.co/papers/2606.09730]]>217ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-10--724458411. SWE-Explore: Benchmarking How Coding Agents Explore Repositories
https://huggingface.co/papers/2606.07297
2. On the Geometry of On-Policy Distillation
https://huggingface.co/papers/2606.07082
3. Agents' Last Exam
https://huggingface.co/papers/2606.05405
4. LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
https://huggingface.co/papers/2606.06087
5. Latent Spatial Memory for Video World Models
https://huggingface.co/papers/2606.09828]]>https://api.spreaker.com/episode/72445841Tue, 09 Jun 2026 23:22:55 +0000ksterx【本日の論文】 1. SWE-Explore: Benchmarking How Coding Agents Explore Repositories https://huggingface.co/papers/2606.07297 2. On the Geometry of On-Policy Distillation https://huggingface.co/papers/2606.07082 3. Agents' Last Exam...1. SWE-Explore: Benchmarking How Coding Agents Explore Repositories
https://huggingface.co/papers/2606.07297
2. On the Geometry of On-Policy Distillation
https://huggingface.co/papers/2606.07082
3. Agents' Last Exam
https://huggingface.co/papers/2606.05405
4. LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
https://huggingface.co/papers/2606.06087
5. Latent Spatial Memory for Video World Models
https://huggingface.co/papers/2606.09828]]>200ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-09--724270011. Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
https://huggingface.co/papers/2606.07502
2. SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations
https://huggingface.co/papers/2606.05563
3. GENEB: Why Genomic Models Are Hard to Compare
https://huggingface.co/papers/2606.04525
4. MMAE: A Massive Multitask Audio Editing Benchmark
https://huggingface.co/papers/2606.07229
5. AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
https://huggingface.co/papers/2606.07326]]>https://api.spreaker.com/episode/72427001Mon, 08 Jun 2026 23:17:47 +0000ksterx【本日の論文】 1. Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings https://huggingface.co/papers/2606.07502 2. SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations...1. Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
https://huggingface.co/papers/2606.07502
2. SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations
https://huggingface.co/papers/2606.05563
3. GENEB: Why Genomic Models Are Hard to Compare
https://huggingface.co/papers/2606.04525
4. MMAE: A Massive Multitask Audio Editing Benchmark
https://huggingface.co/papers/2606.07229
5. AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
https://huggingface.co/papers/2606.07326]]>213ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-08--724084711. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
https://huggingface.co/papers/2606.06492
2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
https://huggingface.co/papers/2606.05553
3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
https://huggingface.co/papers/2606.04743
4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
https://huggingface.co/papers/2606.05622
5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
https://huggingface.co/papers/2606.05259]]>https://api.spreaker.com/episode/72408471Sun, 07 Jun 2026 23:11:34 +0000ksterx【本日の論文】 1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://huggingface.co/papers/2606.06492 2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?...1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
https://huggingface.co/papers/2606.06492
2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
https://huggingface.co/papers/2606.05553
3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
https://huggingface.co/papers/2606.04743
4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
https://huggingface.co/papers/2606.05622
5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
https://huggingface.co/papers/2606.05259]]>275ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-07--723948611. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
https://huggingface.co/papers/2606.06492
2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
https://huggingface.co/papers/2606.05553
3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
https://huggingface.co/papers/2606.04743
4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
https://huggingface.co/papers/2606.05622
5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
https://huggingface.co/papers/2606.05259]]>https://api.spreaker.com/episode/72394861Sat, 06 Jun 2026 23:09:17 +0000ksterx【本日の論文】 1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://huggingface.co/papers/2606.06492 2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?...1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
https://huggingface.co/papers/2606.06492
2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
https://huggingface.co/papers/2606.05553
3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
https://huggingface.co/papers/2606.04743
4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
https://huggingface.co/papers/2606.05622
5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
https://huggingface.co/papers/2606.05259]]>205ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-06--723775811. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
https://huggingface.co/papers/2606.06492
2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
https://huggingface.co/papers/2606.05553
3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
https://huggingface.co/papers/2606.04743
4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
https://huggingface.co/papers/2606.05622
5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
https://huggingface.co/papers/2606.05259]]>https://api.spreaker.com/episode/72377581Fri, 05 Jun 2026 23:14:48 +0000ksterx【本日の論文】 1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://huggingface.co/papers/2606.06492 2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?...1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
https://huggingface.co/papers/2606.06492
2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
https://huggingface.co/papers/2606.05553
3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
https://huggingface.co/papers/2606.04743
4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
https://huggingface.co/papers/2606.05622
5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
https://huggingface.co/papers/2606.05259]]>305ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-05--723554301. Audio Interaction Model
https://huggingface.co/papers/2606.05121
2. Cosmos 3: Omnimodal World Models for Physical AI
https://huggingface.co/papers/2606.02800
3. Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
https://huggingface.co/papers/2606.02060
4. Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
https://huggingface.co/papers/2606.04923
5. OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
https://huggingface.co/papers/2606.03890]]>https://api.spreaker.com/episode/72355430Thu, 04 Jun 2026 23:14:24 +0000ksterx【本日の論文】 1. Audio Interaction Model https://huggingface.co/papers/2606.05121 2. Cosmos 3: Omnimodal World Models for Physical AI https://huggingface.co/papers/2606.02800 3. Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in...1. Audio Interaction Model
https://huggingface.co/papers/2606.05121
2. Cosmos 3: Omnimodal World Models for Physical AI
https://huggingface.co/papers/2606.02800
3. Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
https://huggingface.co/papers/2606.02060
4. Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
https://huggingface.co/papers/2606.04923
5. OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
https://huggingface.co/papers/2606.03890]]>212ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-04--723331641. OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
https://huggingface.co/papers/2606.00683
2. From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain
https://huggingface.co/papers/2605.23895
3. Trust Region On-Policy Distillation
https://huggingface.co/papers/2606.01249
4. Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
https://huggingface.co/papers/2606.03985
5. KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
https://huggingface.co/papers/2606.03458]]>https://api.spreaker.com/episode/72333164Wed, 03 Jun 2026 23:47:15 +0000ksterx【本日の論文】 1. OCC-RAG: Optimal Cognitive Core for Faithful Question Answering https://huggingface.co/papers/2606.00683 2. From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain...1. OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
https://huggingface.co/papers/2606.00683
2. From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain
https://huggingface.co/papers/2605.23895
3. Trust Region On-Policy Distillation
https://huggingface.co/papers/2606.01249
4. Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
https://huggingface.co/papers/2606.03985
5. KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
https://huggingface.co/papers/2606.03458]]>195ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-03--723090241. Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
https://huggingface.co/papers/2605.30611
2. On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
https://huggingface.co/papers/2606.02437
3. A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
https://huggingface.co/papers/2605.28556
4. K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
https://huggingface.co/papers/2606.02404
5. Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
https://huggingface.co/papers/2606.02373]]>https://api.spreaker.com/episode/72309024Tue, 02 Jun 2026 23:50:16 +0000ksterx【本日の論文】 1. Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs https://huggingface.co/papers/2605.30611 2. On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters...1. Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
https://huggingface.co/papers/2605.30611
2. On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
https://huggingface.co/papers/2606.02437
3. A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
https://huggingface.co/papers/2605.28556
4. K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
https://huggingface.co/papers/2606.02404
5. Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
https://huggingface.co/papers/2606.02373]]>213ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-02--722864291. GrepSeek: Training Search Agents for Direct Corpus Interaction
https://huggingface.co/papers/2605.29307
2. COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
https://huggingface.co/papers/2605.31264
3. Trust-Region Behavior Blending for On-Policy Distillation
https://huggingface.co/papers/2605.31159
4. Representation Forcing for Bottleneck-Free Unified Multimodal Models
https://huggingface.co/papers/2605.31604
5. SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
https://huggingface.co/papers/2605.30993]]>https://api.spreaker.com/episode/72286429Mon, 01 Jun 2026 23:31:35 +0000ksterx【本日の論文】 1. GrepSeek: Training Search Agents for Direct Corpus Interaction https://huggingface.co/papers/2605.29307 2. COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation https://huggingface.co/papers/2605.31264 3....1. GrepSeek: Training Search Agents for Direct Corpus Interaction
https://huggingface.co/papers/2605.29307
2. COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
https://huggingface.co/papers/2605.31264
3. Trust-Region Behavior Blending for On-Policy Distillation
https://huggingface.co/papers/2605.31159
4. Representation Forcing for Bottleneck-Free Unified Multimodal Models
https://huggingface.co/papers/2605.31604
5. SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
https://huggingface.co/papers/2605.30993]]>206ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-06-01--722676661. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
https://huggingface.co/papers/2605.29801
2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
https://huggingface.co/papers/2605.30280
3. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
https://huggingface.co/papers/2605.29250
4. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2605.25378
5. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
https://huggingface.co/papers/2605.30263]]>https://api.spreaker.com/episode/72267666Sun, 31 May 2026 23:04:48 +0000ksterx【本日の論文】 1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security https://huggingface.co/papers/2605.29801 2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot...1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
https://huggingface.co/papers/2605.29801
2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
https://huggingface.co/papers/2605.30280
3. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
https://huggingface.co/papers/2605.29250
4. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2605.25378
5. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
https://huggingface.co/papers/2605.30263]]>191ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-31--722556371. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
https://huggingface.co/papers/2605.29801
2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
https://huggingface.co/papers/2605.30280
3. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
https://huggingface.co/papers/2605.29250
4. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2605.25378
5. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
https://huggingface.co/papers/2605.30263]]>https://api.spreaker.com/episode/72255637Sat, 30 May 2026 23:02:32 +0000ksterx【本日の論文】 1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security https://huggingface.co/papers/2605.29801 2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot...1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
https://huggingface.co/papers/2605.29801
2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
https://huggingface.co/papers/2605.30280
3. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
https://huggingface.co/papers/2605.29250
4. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2605.25378
5. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
https://huggingface.co/papers/2605.30263]]>248ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-30--722360741. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
https://huggingface.co/papers/2605.29801
2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
https://huggingface.co/papers/2605.30280
3. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
https://huggingface.co/papers/2605.29250
4. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2605.25378
5. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
https://huggingface.co/papers/2605.30263]]>https://api.spreaker.com/episode/72236074Fri, 29 May 2026 23:18:18 +0000ksterx【本日の論文】 1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security https://huggingface.co/papers/2605.29801 2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot...1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
https://huggingface.co/papers/2605.29801
2. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
https://huggingface.co/papers/2605.30280
3. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
https://huggingface.co/papers/2605.29250
4. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
https://huggingface.co/papers/2605.25378
5. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
https://huggingface.co/papers/2605.30263]]>236ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-29--722166651. Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
https://huggingface.co/papers/2605.28816
2. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
https://huggingface.co/papers/2605.28293
3. Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
https://huggingface.co/papers/2605.28774
4. From Pixels to Words -- Towards Native One-Vision Models at Scale
https://huggingface.co/papers/2605.28820
5. Self-Improving Language Models with Bidirectional Evolutionary Search
https://huggingface.co/papers/2605.28814]]>https://api.spreaker.com/episode/72216665Thu, 28 May 2026 23:21:24 +0000ksterx【本日の論文】 1. Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players https://huggingface.co/papers/2605.28816 2. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation...1. Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
https://huggingface.co/papers/2605.28816
2. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
https://huggingface.co/papers/2605.28293
3. Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
https://huggingface.co/papers/2605.28774
4. From Pixels to Words -- Towards Native One-Vision Models at Scale
https://huggingface.co/papers/2605.28820
5. Self-Improving Language Models with Bidirectional Evolutionary Search
https://huggingface.co/papers/2605.28814]]>204ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-28--721955131. LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
https://huggingface.co/papers/2605.27365
2. EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
https://huggingface.co/papers/2605.23271
3. SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
https://huggingface.co/papers/2605.27367
4. MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
https://huggingface.co/papers/2605.26114
5. Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
https://huggingface.co/papers/2605.26230]]>https://api.spreaker.com/episode/72195513Wed, 27 May 2026 23:22:49 +0000ksterx【本日の論文】 1. LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding https://huggingface.co/papers/2605.27365 2. EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video...1. LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
https://huggingface.co/papers/2605.27365
2. EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
https://huggingface.co/papers/2605.23271
3. SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
https://huggingface.co/papers/2605.27367
4. MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
https://huggingface.co/papers/2605.26114
5. Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
https://huggingface.co/papers/2605.26230]]>245ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-27--721770961. DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
https://huggingface.co/papers/2605.25604
2. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
https://huggingface.co/papers/2605.25874
3. Macaron-A2UI: A Model for Generative UI in Personal Agents
https://huggingface.co/papers/2605.24830
4. Foundation Protocol: A Coordination Layer for Agentic Society
https://huggingface.co/papers/2605.23218
5. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
https://huggingface.co/papers/2605.26115]]>https://api.spreaker.com/episode/72177096Tue, 26 May 2026 23:16:19 +0000ksterx【本日の論文】 1. DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning https://huggingface.co/papers/2605.25604 2. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation...1. DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
https://huggingface.co/papers/2605.25604
2. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
https://huggingface.co/papers/2605.25874
3. Macaron-A2UI: A Model for Generative UI in Personal Agents
https://huggingface.co/papers/2605.24830
4. Foundation Protocol: A Coordination Layer for Agentic Society
https://huggingface.co/papers/2605.23218
5. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
https://huggingface.co/papers/2605.26115]]>287ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-26--721603801. SkillOpt: Executive Strategy for Self-Evolving Agent Skills
https://huggingface.co/papers/2605.23904
2. Rethinking Cross-Layer Information Routing in Diffusion Transformers
https://huggingface.co/papers/2605.20708
3. Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
https://huggingface.co/papers/2605.21573
4. SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
https://huggingface.co/papers/2605.22878
5. StepAudio 2.5 Technical Report
https://huggingface.co/papers/2605.23463]]>https://api.spreaker.com/episode/72160380Mon, 25 May 2026 23:06:36 +0000ksterx【本日の論文】 1. SkillOpt: Executive Strategy for Self-Evolving Agent Skills https://huggingface.co/papers/2605.23904 2. Rethinking Cross-Layer Information Routing in Diffusion Transformers https://huggingface.co/papers/2605.20708 3. Lens: Rethinking...1. SkillOpt: Executive Strategy for Self-Evolving Agent Skills
https://huggingface.co/papers/2605.23904
2. Rethinking Cross-Layer Information Routing in Diffusion Transformers
https://huggingface.co/papers/2605.20708
3. Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
https://huggingface.co/papers/2605.21573
4. SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
https://huggingface.co/papers/2605.22878
5. StepAudio 2.5 Technical Report
https://huggingface.co/papers/2605.23463]]>165ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-25--721472781. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
https://huggingface.co/papers/2605.21467
2. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
https://huggingface.co/papers/2605.22355
3. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
https://huggingface.co/papers/2605.22109
4. π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
https://huggingface.co/papers/2605.14678
5. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
https://huggingface.co/papers/2605.16928]]>https://api.spreaker.com/episode/72147278Sun, 24 May 2026 23:03:38 +0000ksterx【本日の論文】 1. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards https://huggingface.co/papers/2605.21467 2. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation...1. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
https://huggingface.co/papers/2605.21467
2. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
https://huggingface.co/papers/2605.22355
3. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
https://huggingface.co/papers/2605.22109
4. π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
https://huggingface.co/papers/2605.14678
5. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
https://huggingface.co/papers/2605.16928]]>215ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-24--721350891. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
https://huggingface.co/papers/2605.21467
2. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
https://huggingface.co/papers/2605.22355
3. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
https://huggingface.co/papers/2605.22109
4. π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
https://huggingface.co/papers/2605.14678
5. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
https://huggingface.co/papers/2605.16928]]>https://api.spreaker.com/episode/72135089Sat, 23 May 2026 23:00:21 +0000ksterx【本日の論文】 1. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards https://huggingface.co/papers/2605.21467 2. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation...1. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
https://huggingface.co/papers/2605.21467
2. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
https://huggingface.co/papers/2605.22355
3. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
https://huggingface.co/papers/2605.22109
4. π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
https://huggingface.co/papers/2605.14678
5. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
https://huggingface.co/papers/2605.16928]]>314ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-23--721222171. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
https://huggingface.co/papers/2605.22355
2. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
https://huggingface.co/papers/2605.22109
3. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
https://huggingface.co/papers/2605.21467
4. π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
https://huggingface.co/papers/2605.14678
5. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
https://huggingface.co/papers/2605.16928]]>https://api.spreaker.com/episode/72122217Fri, 22 May 2026 23:05:03 +0000ksterx【本日の論文】 1. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation https://huggingface.co/papers/2605.22355 2. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?...1. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
https://huggingface.co/papers/2605.22355
2. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
https://huggingface.co/papers/2605.22109
3. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
https://huggingface.co/papers/2605.21467
4. π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
https://huggingface.co/papers/2605.14678
5. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
https://huggingface.co/papers/2605.16928]]>219ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-22--721053731. Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
https://huggingface.co/papers/2605.19833
2. Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
https://huggingface.co/papers/2605.14747
3. Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
https://huggingface.co/papers/2605.18233
4. IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
https://huggingface.co/papers/2605.20682
5. You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
https://huggingface.co/papers/2605.21468]]>https://api.spreaker.com/episode/72105373Thu, 21 May 2026 23:09:47 +0000ksterx【本日の論文】 1. Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation https://huggingface.co/papers/2605.19833 2. Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent...1. Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
https://huggingface.co/papers/2605.19833
2. Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
https://huggingface.co/papers/2605.14747
3. Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
https://huggingface.co/papers/2605.18233
4. IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
https://huggingface.co/papers/2605.20682
5. You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
https://huggingface.co/papers/2605.21468]]>263ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-21--720913341. When Vision Speaks for Sound
https://huggingface.co/papers/2605.16403
2. Active Learners as Efficient PRP Rerankers
https://huggingface.co/papers/2605.14236
3. Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
https://huggingface.co/papers/2605.11609
4. GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
https://huggingface.co/papers/2605.19577
5. OpenComputer: Verifiable Software Worlds for Computer-Use Agents
https://huggingface.co/papers/2605.19769]]>https://api.spreaker.com/episode/72091334Wed, 20 May 2026 23:18:24 +0000ksterx【本日の論文】 1. When Vision Speaks for Sound https://huggingface.co/papers/2605.16403 2. Active Learners as Efficient PRP Rerankers https://huggingface.co/papers/2605.14236 3. Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information...1. When Vision Speaks for Sound
https://huggingface.co/papers/2605.16403
2. Active Learners as Efficient PRP Rerankers
https://huggingface.co/papers/2605.14236
3. Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
https://huggingface.co/papers/2605.11609
4. GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
https://huggingface.co/papers/2605.19577
5. OpenComputer: Verifiable Software Worlds for Computer-Use Agents
https://huggingface.co/papers/2605.19769]]>190ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-20--720760351. Code as Agent Harness
https://huggingface.co/papers/2605.18747
2. SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
https://huggingface.co/papers/2605.18401
3. LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
https://huggingface.co/papers/2605.18739
4. Lance: Unified Multimodal Modeling by Multi-Task Synergy
https://huggingface.co/papers/2605.18678
5. AI for Auto-Research: Roadmap & User Guide
https://huggingface.co/papers/2605.18661]]>https://api.spreaker.com/episode/72076035Tue, 19 May 2026 23:08:09 +0000ksterx【本日の論文】 1. Code as Agent Harness https://huggingface.co/papers/2605.18747 2. SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution https://huggingface.co/papers/2605.18401 3. LongLive-2.0: An NVFP4...1. Code as Agent Harness
https://huggingface.co/papers/2605.18747
2. SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
https://huggingface.co/papers/2605.18401
3. LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
https://huggingface.co/papers/2605.18739
4. Lance: Unified Multimodal Modeling by Multi-Task Synergy
https://huggingface.co/papers/2605.18678
5. AI for Auto-Research: Roadmap & User Guide
https://huggingface.co/papers/2605.18661]]>211ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-19--720617231. CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
https://huggingface.co/papers/2605.12882
2. PhysBrain 1.0 Technical Report
https://huggingface.co/papers/2605.15298
3. MMSkills: Towards Multimodal Skills for General Visual Agents
https://huggingface.co/papers/2605.13527
4. FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
https://huggingface.co/papers/2605.15824
5. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
https://huggingface.co/papers/2605.11739]]>https://api.spreaker.com/episode/72061723Mon, 18 May 2026 23:07:56 +0000ksterx【本日の論文】 1. CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence https://huggingface.co/papers/2605.12882 2. PhysBrain 1.0 Technical Report https://huggingface.co/papers/2605.15298 3. MMSkills: Towards Multimodal...1. CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
https://huggingface.co/papers/2605.12882
2. PhysBrain 1.0 Technical Report
https://huggingface.co/papers/2605.15298
3. MMSkills: Towards Multimodal Skills for General Visual Agents
https://huggingface.co/papers/2605.13527
4. FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
https://huggingface.co/papers/2605.15824
5. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
https://huggingface.co/papers/2605.11739]]>209ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-18--720479231. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
https://huggingface.co/papers/2605.13301
2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
https://huggingface.co/papers/2605.15141
3. Self-Distilled Agentic Reinforcement Learning
https://huggingface.co/papers/2605.15155
4. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
https://huggingface.co/papers/2605.14906
5. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
https://huggingface.co/papers/2605.15178]]>https://api.spreaker.com/episode/72047923Sun, 17 May 2026 23:01:21 +0000ksterx【本日の論文】 1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling https://huggingface.co/papers/2605.13301 2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation...1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
https://huggingface.co/papers/2605.13301
2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
https://huggingface.co/papers/2605.15141
3. Self-Distilled Agentic Reinforcement Learning
https://huggingface.co/papers/2605.15155
4. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
https://huggingface.co/papers/2605.14906
5. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
https://huggingface.co/papers/2605.15178]]>306ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-17--720362331. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
https://huggingface.co/papers/2605.13301
2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
https://huggingface.co/papers/2605.15141
3. Self-Distilled Agentic Reinforcement Learning
https://huggingface.co/papers/2605.15155
4. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
https://huggingface.co/papers/2605.14906
5. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
https://huggingface.co/papers/2605.15178]]>https://api.spreaker.com/episode/72036233Sat, 16 May 2026 22:50:20 +0000ksterx【本日の論文】 1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling https://huggingface.co/papers/2605.13301 2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation...1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
https://huggingface.co/papers/2605.13301
2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
https://huggingface.co/papers/2605.15141
3. Self-Distilled Agentic Reinforcement Learning
https://huggingface.co/papers/2605.15155
4. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
https://huggingface.co/papers/2605.14906
5. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
https://huggingface.co/papers/2605.15178]]>281ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-16--720263041. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
https://huggingface.co/papers/2605.13301
2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
https://huggingface.co/papers/2605.15141
3. Self-Distilled Agentic Reinforcement Learning
https://huggingface.co/papers/2605.15155
4. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
https://huggingface.co/papers/2605.14906
5. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
https://huggingface.co/papers/2605.15178]]>https://api.spreaker.com/episode/72026304Fri, 15 May 2026 23:00:43 +0000ksterx【本日の論文】 1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling https://huggingface.co/papers/2605.13301 2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation...1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
https://huggingface.co/papers/2605.13301
2. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
https://huggingface.co/papers/2605.15141
3. Self-Distilled Agentic Reinforcement Learning
https://huggingface.co/papers/2605.15155
4. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
https://huggingface.co/papers/2605.14906
5. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
https://huggingface.co/papers/2605.15178]]>235ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-15--720127551. MinT: Managed Infrastructure for Training and Serving Millions of LLMs
https://huggingface.co/papers/2605.13779
2. MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
https://huggingface.co/papers/2605.10616
3. AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
https://huggingface.co/papers/2605.13724
4. Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
https://huggingface.co/papers/2605.13831
5. EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
https://huggingface.co/papers/2605.13841]]>https://api.spreaker.com/episode/72012755Thu, 14 May 2026 23:03:26 +0000ksterx【本日の論文】 1. MinT: Managed Infrastructure for Training and Serving Millions of LLMs https://huggingface.co/papers/2605.13779 2. MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image https://huggingface.co/papers/2605.10616 3....1. MinT: Managed Infrastructure for Training and Serving Millions of LLMs
https://huggingface.co/papers/2605.13779
2. MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
https://huggingface.co/papers/2605.10616
3. AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
https://huggingface.co/papers/2605.13724
4. Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
https://huggingface.co/papers/2605.13831
5. EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
https://huggingface.co/papers/2605.13841]]>308ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-14--719975531. MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
https://huggingface.co/papers/2605.09530
2. SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
https://huggingface.co/papers/2605.12500
3. δ-mem: Efficient Online Memory for Large Language Models
https://huggingface.co/papers/2605.12357
4. RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
https://huggingface.co/papers/2605.10899
5. Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
https://huggingface.co/papers/2605.12178]]>https://api.spreaker.com/episode/71997553Wed, 13 May 2026 23:11:41 +0000ksterx【本日の論文】 1. MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents https://huggingface.co/papers/2605.09530 2. SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture...1. MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
https://huggingface.co/papers/2605.09530
2. SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
https://huggingface.co/papers/2605.12500
3. δ-mem: Efficient Online Memory for Large Language Models
https://huggingface.co/papers/2605.12357
4. RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
https://huggingface.co/papers/2605.10899
5. Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
https://huggingface.co/papers/2605.12178]]>217ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-13--719835131. Qwen-Image-2.0 Technical Report
https://huggingface.co/papers/2605.10730
2. Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
https://huggingface.co/papers/2605.09063
3. CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
https://huggingface.co/papers/2605.08735
4. TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
https://huggingface.co/papers/2605.10344
5. PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
https://huggingface.co/papers/2605.10341]]>https://api.spreaker.com/episode/71983513Tue, 12 May 2026 23:07:00 +0000ksterx【本日の論文】 1. Qwen-Image-2.0 Technical Report https://huggingface.co/papers/2605.10730 2. Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs https://huggingface.co/papers/2605.09063 3. CollabVR:...1. Qwen-Image-2.0 Technical Report
https://huggingface.co/papers/2605.10730
2. Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
https://huggingface.co/papers/2605.09063
3. CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
https://huggingface.co/papers/2605.08735
4. TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
https://huggingface.co/papers/2605.10344
5. PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
https://huggingface.co/papers/2605.10341]]>234ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-12--719639001. Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers
https://huggingface.co/papers/2605.06169
2. MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
https://huggingface.co/papers/2512.18181
3. Flow-OPD: On-Policy Distillation for Flow Matching Models
https://huggingface.co/papers/2605.08063
4. HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
https://huggingface.co/papers/2605.07177
5. Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
https://huggingface.co/papers/2605.06139]]>https://api.spreaker.com/episode/71963900Mon, 11 May 2026 23:00:19 +0000ksterx【本日の論文】 1. Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers https://huggingface.co/papers/2605.06169 2. MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation...1. Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers
https://huggingface.co/papers/2605.06169
2. MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
https://huggingface.co/papers/2512.18181
3. Flow-OPD: On-Policy Distillation for Flow Matching Models
https://huggingface.co/papers/2605.08063
4. HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
https://huggingface.co/papers/2605.07177
5. Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
https://huggingface.co/papers/2605.06139]]>181ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-11--719502671. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
https://huggingface.co/papers/2605.05242
2. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
https://huggingface.co/papers/2605.06130
3. Continuous Latent Diffusion Language Model
https://huggingface.co/papers/2605.06548
4. MiA-Signature: Approximating Global Activation for Long-Context Understanding
https://huggingface.co/papers/2605.06416
5. RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
https://huggingface.co/papers/2605.04523]]>https://api.spreaker.com/episode/71950267Sun, 10 May 2026 22:53:05 +0000ksterx【本日の論文】 1. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction https://huggingface.co/papers/2605.05242 2. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning...1. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
https://huggingface.co/papers/2605.05242
2. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
https://huggingface.co/papers/2605.06130
3. Continuous Latent Diffusion Language Model
https://huggingface.co/papers/2605.06548
4. MiA-Signature: Approximating Global Activation for Long-Context Understanding
https://huggingface.co/papers/2605.06416
5. RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
https://huggingface.co/papers/2605.04523]]>224ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-10--719420331. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
https://huggingface.co/papers/2605.05242
2. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
https://huggingface.co/papers/2605.06130
3. Continuous Latent Diffusion Language Model
https://huggingface.co/papers/2605.06548
4. MiA-Signature: Approximating Global Activation for Long-Context Understanding
https://huggingface.co/papers/2605.06416
5. RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
https://huggingface.co/papers/2605.04523]]>https://api.spreaker.com/episode/71942033Sat, 09 May 2026 22:48:50 +0000ksterx【本日の論文】 1. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction https://huggingface.co/papers/2605.05242 2. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning...1. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
https://huggingface.co/papers/2605.05242
2. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
https://huggingface.co/papers/2605.06130
3. Continuous Latent Diffusion Language Model
https://huggingface.co/papers/2605.06548
4. MiA-Signature: Approximating Global Activation for Long-Context Understanding
https://huggingface.co/papers/2605.06416
5. RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
https://huggingface.co/papers/2605.04523]]>226ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-09--719314311. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
https://huggingface.co/papers/2605.06130
2. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
https://huggingface.co/papers/2605.05242
3. Continuous Latent Diffusion Language Model
https://huggingface.co/papers/2605.06548
4. MiA-Signature: Approximating Global Activation for Long-Context Understanding
https://huggingface.co/papers/2605.06416
5. RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
https://huggingface.co/papers/2605.04523]]>https://api.spreaker.com/episode/71931431Fri, 08 May 2026 23:00:12 +0000ksterx【本日の論文】 1. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning https://huggingface.co/papers/2605.06130 2. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction...1. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
https://huggingface.co/papers/2605.06130
2. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
https://huggingface.co/papers/2605.05242
3. Continuous Latent Diffusion Language Model
https://huggingface.co/papers/2605.06548
4. MiA-Signature: Approximating Global Activation for Long-Context Understanding
https://huggingface.co/papers/2605.06416
5. RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
https://huggingface.co/papers/2605.04523]]>200ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-08--719142801. Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
https://huggingface.co/papers/2605.03849
2. Stream-T1: Test-Time Scaling for Streaming Video Generation
https://huggingface.co/papers/2605.04461
3. RLDX-1 Technical Report
https://huggingface.co/papers/2605.03269
4. OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
https://huggingface.co/papers/2605.05185
5. HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
https://huggingface.co/papers/2604.28196]]>https://api.spreaker.com/episode/71914280Thu, 07 May 2026 23:07:44 +0000ksterx【本日の論文】 1. Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation https://huggingface.co/papers/2605.03849 2. Stream-T1: Test-Time Scaling for Streaming Video Generation...1. Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
https://huggingface.co/papers/2605.03849
2. Stream-T1: Test-Time Scaling for Streaming Video Generation
https://huggingface.co/papers/2605.04461
3. RLDX-1 Technical Report
https://huggingface.co/papers/2605.03269
4. OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
https://huggingface.co/papers/2605.05185
5. HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
https://huggingface.co/papers/2604.28196]]>234ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-07--718992401. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
https://huggingface.co/papers/2605.03042
2. OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
https://huggingface.co/papers/2605.04036
3. Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
https://huggingface.co/papers/2604.28123
4. X2SAM: Any Segmentation in Images and Videos
https://huggingface.co/papers/2605.00891
5. HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
https://huggingface.co/papers/2605.02396]]>https://api.spreaker.com/episode/71899240Wed, 06 May 2026 23:02:12 +0000ksterx【本日の論文】 1. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration https://huggingface.co/papers/2605.03042 2. OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories...1. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
https://huggingface.co/papers/2605.03042
2. OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
https://huggingface.co/papers/2605.04036
3. Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
https://huggingface.co/papers/2604.28123
4. X2SAM: Any Segmentation in Images and Videos
https://huggingface.co/papers/2605.00891
5. HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
https://huggingface.co/papers/2605.02396]]>206ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-06--718819631. MolmoAct2: Action Reasoning Models for Real-world Deployment
https://huggingface.co/papers/2605.02881
2. From Context to Skills: Can Language Models Learn from Context Skillfully?
https://huggingface.co/papers/2604.27660
3. Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
https://huggingface.co/papers/2605.00814
4. Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling
https://huggingface.co/papers/2604.28075
5. OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
https://huggingface.co/papers/2605.00877]]>https://api.spreaker.com/episode/71881963Tue, 05 May 2026 23:01:23 +0000ksterx【本日の論文】 1. MolmoAct2: Action Reasoning Models for Real-world Deployment https://huggingface.co/papers/2605.02881 2. From Context to Skills: Can Language Models Learn from Context Skillfully? https://huggingface.co/papers/2604.27660 3. Persistent...1. MolmoAct2: Action Reasoning Models for Real-world Deployment
https://huggingface.co/papers/2605.02881
2. From Context to Skills: Can Language Models Learn from Context Skillfully?
https://huggingface.co/papers/2604.27660
3. Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
https://huggingface.co/papers/2605.00814
4. Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling
https://huggingface.co/papers/2604.28075
5. OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
https://huggingface.co/papers/2605.00877]]>296ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-05--718661141. UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
https://huggingface.co/papers/2605.00658
2. Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
https://huggingface.co/papers/2604.27221
3. Map2World: Segment Map Conditioned Text to 3D World Generation
https://huggingface.co/papers/2605.00781
4. Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
https://huggingface.co/papers/2604.23774
5. From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
https://huggingface.co/papers/2604.24026]]>https://api.spreaker.com/episode/71866114Mon, 04 May 2026 23:02:47 +0000ksterx【本日の論文】 1. UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors https://huggingface.co/papers/2605.00658 2. Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction...1. UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
https://huggingface.co/papers/2605.00658
2. Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
https://huggingface.co/papers/2604.27221
3. Map2World: Segment Map Conditioned Text to 3D World Generation
https://huggingface.co/papers/2605.00781
4. Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
https://huggingface.co/papers/2604.23774
5. From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
https://huggingface.co/papers/2604.24026]]>228ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-04--718440391. Heterogeneous Scientific Foundation Model Collaboration
https://huggingface.co/papers/2604.27351
2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
https://huggingface.co/papers/2604.28185
3. Co-Evolving Policy Distillation
https://huggingface.co/papers/2604.27083
4. Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
https://huggingface.co/papers/2604.28158
5. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
https://huggingface.co/papers/2604.27711]]>https://api.spreaker.com/episode/71844039Sun, 03 May 2026 22:46:50 +0000ksterx【本日の論文】 1. Heterogeneous Scientific Foundation Model Collaboration https://huggingface.co/papers/2604.27351 2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://huggingface.co/papers/2604.28185...1. Heterogeneous Scientific Foundation Model Collaboration
https://huggingface.co/papers/2604.27351
2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
https://huggingface.co/papers/2604.28185
3. Co-Evolving Policy Distillation
https://huggingface.co/papers/2604.27083
4. Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
https://huggingface.co/papers/2604.28158
5. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
https://huggingface.co/papers/2604.27711]]>224ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-03--718328531. Heterogeneous Scientific Foundation Model Collaboration
https://huggingface.co/papers/2604.27351
2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
https://huggingface.co/papers/2604.28185
3. Co-Evolving Policy Distillation
https://huggingface.co/papers/2604.27083
4. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
https://huggingface.co/papers/2604.27711
5. Efficient Training on Multiple Consumer GPUs with RoundPipe
https://huggingface.co/papers/2604.27085]]>https://api.spreaker.com/episode/71832853Sat, 02 May 2026 22:46:25 +0000ksterx【本日の論文】 1. Heterogeneous Scientific Foundation Model Collaboration https://huggingface.co/papers/2604.27351 2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://huggingface.co/papers/2604.28185...1. Heterogeneous Scientific Foundation Model Collaboration
https://huggingface.co/papers/2604.27351
2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
https://huggingface.co/papers/2604.28185
3. Co-Evolving Policy Distillation
https://huggingface.co/papers/2604.27083
4. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
https://huggingface.co/papers/2604.27711
5. Efficient Training on Multiple Consumer GPUs with RoundPipe
https://huggingface.co/papers/2604.27085]]>189ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-02--718215311. Heterogeneous Scientific Foundation Model Collaboration
https://huggingface.co/papers/2604.27351
2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
https://huggingface.co/papers/2604.28185
3. Co-Evolving Policy Distillation
https://huggingface.co/papers/2604.27083
4. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
https://huggingface.co/papers/2604.27711
5. Efficient Training on Multiple Consumer GPUs with RoundPipe
https://huggingface.co/papers/2604.27085]]>https://api.spreaker.com/episode/71821531Fri, 01 May 2026 22:56:59 +0000ksterx【本日の論文】 1. Heterogeneous Scientific Foundation Model Collaboration https://huggingface.co/papers/2604.27351 2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://huggingface.co/papers/2604.28185...1. Heterogeneous Scientific Foundation Model Collaboration
https://huggingface.co/papers/2604.27351
2. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
https://huggingface.co/papers/2604.28185
3. Co-Evolving Policy Distillation
https://huggingface.co/papers/2604.27083
4. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
https://huggingface.co/papers/2604.27711
5. Efficient Training on Multiple Consumer GPUs with RoundPipe
https://huggingface.co/papers/2604.27085]]>266ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-05-01--717983241. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
https://huggingface.co/papers/2604.26752
2. Large Language Models Explore by Latent Distilling
https://huggingface.co/papers/2604.24927
3. RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments
https://huggingface.co/papers/2604.26067
4. ClawGym: A Scalable Framework for Building Effective Claw Agents
https://huggingface.co/papers/2604.26904
5. Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
https://huggingface.co/papers/2604.26951]]>https://api.spreaker.com/episode/71798324Thu, 30 Apr 2026 22:58:41 +0000ksterx【本日の論文】 1. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://huggingface.co/papers/2604.26752 2. Large Language Models Explore by Latent Distilling https://huggingface.co/papers/2604.24927 3. RADIO-ViPE: Online Tightly...1. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
https://huggingface.co/papers/2604.26752
2. Large Language Models Explore by Latent Distilling
https://huggingface.co/papers/2604.24927
3. RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments
https://huggingface.co/papers/2604.26067
4. ClawGym: A Scalable Framework for Building Effective Claw Agents
https://huggingface.co/papers/2604.26904
5. Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
https://huggingface.co/papers/2604.26951]]>190ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-30--717591831. Recursive Multi-Agent Systems
https://huggingface.co/papers/2604.25917
2. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
https://huggingface.co/papers/2604.24819
3. DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
https://huggingface.co/papers/2604.25914
4. AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
https://huggingface.co/papers/2604.25256
5. Meta-CoT: Enhancing Granularity and Generalization in Image Editing
https://huggingface.co/papers/2604.24625]]>https://api.spreaker.com/episode/71759183Wed, 29 Apr 2026 23:02:31 +0000ksterx【本日の論文】 1. Recursive Multi-Agent Systems https://huggingface.co/papers/2604.25917 2. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora https://huggingface.co/papers/2604.24819 3. DV-World: Benchmarking...1. Recursive Multi-Agent Systems
https://huggingface.co/papers/2604.25917
2. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
https://huggingface.co/papers/2604.24819
3. DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
https://huggingface.co/papers/2604.25914
4. AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
https://huggingface.co/papers/2604.25256
5. Meta-CoT: Enhancing Granularity and Generalization in Image Editing
https://huggingface.co/papers/2604.24625]]>198ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-29--717177981. From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
https://huggingface.co/papers/2604.22446
2. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
https://huggingface.co/papers/2604.24764
3. ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
https://huggingface.co/papers/2604.24300
4. Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
https://huggingface.co/papers/2604.24763
5. Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
https://huggingface.co/papers/2604.23775]]>https://api.spreaker.com/episode/71717798Tue, 28 Apr 2026 23:02:23 +0000ksterx【本日の論文】 1. From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company https://huggingface.co/papers/2604.22446 2. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation https://huggingface.co/papers/2604.24764 3....1. From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
https://huggingface.co/papers/2604.22446
2. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
https://huggingface.co/papers/2604.24764
3. ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
https://huggingface.co/papers/2604.24300
4. Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
https://huggingface.co/papers/2604.24763
5. Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
https://huggingface.co/papers/2604.23775]]>196ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-28--716869501. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
https://huggingface.co/papers/2604.22748
2. Video Analysis and Generation via a Semantic Progress Function
https://huggingface.co/papers/2604.22554
3. DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction
https://huggingface.co/papers/2604.21518
4. LLM Safety From Within: Detecting Harmful Content with Internal Representations
https://huggingface.co/papers/2604.18519
5. FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing
https://huggingface.co/papers/2604.22586]]>https://api.spreaker.com/episode/71686950Mon, 27 Apr 2026 22:59:22 +0000ksterx【本日の論文】 1. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond https://huggingface.co/papers/2604.22748 2. Video Analysis and Generation via a Semantic Progress Function https://huggingface.co/papers/2604.22554 3. DiffNR:...1. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
https://huggingface.co/papers/2604.22748
2. Video Analysis and Generation via a Semantic Progress Function
https://huggingface.co/papers/2604.22554
3. DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction
https://huggingface.co/papers/2604.21518
4. LLM Safety From Within: Detecting Harmful Content with Internal Representations
https://huggingface.co/papers/2604.18519
5. FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing
https://huggingface.co/papers/2604.22586]]>316ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-27--716605591. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
https://huggingface.co/papers/2604.17295
2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models
https://huggingface.co/papers/2604.21686
3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
https://huggingface.co/papers/2604.19734
4. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
https://huggingface.co/papers/2604.21689
5. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
https://huggingface.co/papers/2604.20987]]>https://api.spreaker.com/episode/71660559Sun, 26 Apr 2026 22:42:48 +0000ksterx【本日の論文】 1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://huggingface.co/papers/2604.17295 2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models...1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
https://huggingface.co/papers/2604.17295
2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models
https://huggingface.co/papers/2604.21686
3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
https://huggingface.co/papers/2604.19734
4. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
https://huggingface.co/papers/2604.21689
5. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
https://huggingface.co/papers/2604.20987]]>209ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-26--716433471. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
https://huggingface.co/papers/2604.17295
2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models
https://huggingface.co/papers/2604.21686
3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
https://huggingface.co/papers/2604.19734
4. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
https://huggingface.co/papers/2604.21689
5. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
https://huggingface.co/papers/2604.20987]]>https://api.spreaker.com/episode/71643347Sat, 25 Apr 2026 22:42:39 +0000ksterx【本日の論文】 1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://huggingface.co/papers/2604.17295 2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models...1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
https://huggingface.co/papers/2604.17295
2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models
https://huggingface.co/papers/2604.21686
3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
https://huggingface.co/papers/2604.19734
4. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
https://huggingface.co/papers/2604.21689
5. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
https://huggingface.co/papers/2604.20987]]>300ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-25--716227741. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
https://huggingface.co/papers/2604.17295
2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models
https://huggingface.co/papers/2604.21686
3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
https://huggingface.co/papers/2604.19734
4. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
https://huggingface.co/papers/2604.21689
5. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
https://huggingface.co/papers/2604.20987]]>https://api.spreaker.com/episode/71622774Fri, 24 Apr 2026 22:44:53 +0000ksterx【本日の論文】 1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://huggingface.co/papers/2604.17295 2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models...1. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
https://huggingface.co/papers/2604.17295
2. WorldMark: A Unified Benchmark Suite for Interactive Video World Models
https://huggingface.co/papers/2604.21686
3. UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
https://huggingface.co/papers/2604.19734
4. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
https://huggingface.co/papers/2604.21689
5. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
https://huggingface.co/papers/2604.20987]]>240ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-24--715988271. LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
https://huggingface.co/papers/2604.20796
2. Near-Future Policy Optimization
https://huggingface.co/papers/2604.20733
3. DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
https://huggingface.co/papers/2604.19859
4. OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
https://huggingface.co/papers/2604.15093
5. DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
https://huggingface.co/papers/2604.20841]]>https://api.spreaker.com/episode/71598827Thu, 23 Apr 2026 22:48:13 +0000ksterx【本日の論文】 1. LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model https://huggingface.co/papers/2604.20796 2. Near-Future Policy Optimization https://huggingface.co/papers/2604.20733 3. DR-Venus:...1. LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
https://huggingface.co/papers/2604.20796
2. Near-Future Policy Optimization
https://huggingface.co/papers/2604.20733
3. DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
https://huggingface.co/papers/2604.19859
4. OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
https://huggingface.co/papers/2604.15093
5. DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
https://huggingface.co/papers/2604.20841]]>206ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-23--715739091. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
https://huggingface.co/papers/2604.19748
2. CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
https://huggingface.co/papers/2604.19636
3. AgentSPEX: An Agent SPecification and EXecution Language
https://huggingface.co/papers/2604.13346
4. AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
https://huggingface.co/papers/2604.19747
5. TEMPO: Scaling Test-time Training for Large Reasoning Models
https://huggingface.co/papers/2604.19295]]>https://api.spreaker.com/episode/71573909Wed, 22 Apr 2026 22:53:09 +0000ksterx【本日の論文】 1. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items https://huggingface.co/papers/2604.19748 2. CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation...1. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
https://huggingface.co/papers/2604.19748
2. CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
https://huggingface.co/papers/2604.19636
3. AgentSPEX: An Agent SPecification and EXecution Language
https://huggingface.co/papers/2604.13346
4. AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
https://huggingface.co/papers/2604.19747
5. TEMPO: Scaling Test-time Training for Large Reasoning Models
https://huggingface.co/papers/2604.19295]]>186ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-22--715354251. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
https://huggingface.co/papers/2604.18168
2. OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
https://huggingface.co/papers/2604.18486
3. Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
https://huggingface.co/papers/2604.18292
4. OpenGame: Open Agentic Coding for Games
https://huggingface.co/papers/2604.18394
5. MultiWorld: Scalable Multi-Agent Multi-View Video World Models
https://huggingface.co/papers/2604.18564]]>https://api.spreaker.com/episode/71535425Tue, 21 Apr 2026 22:43:57 +0000ksterx【本日の論文】 1. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation https://huggingface.co/papers/2604.18168 2. OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation...1. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
https://huggingface.co/papers/2604.18168
2. OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
https://huggingface.co/papers/2604.18486
3. Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
https://huggingface.co/papers/2604.18292
4. OpenGame: Open Agentic Coding for Games
https://huggingface.co/papers/2604.18394
5. MultiWorld: Scalable Multi-Agent Multi-View Video World Models
https://huggingface.co/papers/2604.18564]]>242ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-21--715053491. Elucidating the SNR-t Bias of Diffusion Probabilistic Models
https://huggingface.co/papers/2604.16044
2. Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
https://huggingface.co/papers/2502.07408
3. PersonaVLM: Long-Term Personalized Multimodal LLMs
https://huggingface.co/papers/2604.13074
4. Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems
https://huggingface.co/papers/2604.04936
5. Qwen3.5-Omni Technical Report
https://huggingface.co/papers/2604.15804]]>https://api.spreaker.com/episode/71505349Mon, 20 Apr 2026 22:49:28 +0000ksterx【本日の論文】 1. Elucidating the SNR-t Bias of Diffusion Probabilistic Models https://huggingface.co/papers/2604.16044 2. Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips...1. Elucidating the SNR-t Bias of Diffusion Probabilistic Models
https://huggingface.co/papers/2604.16044
2. Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
https://huggingface.co/papers/2502.07408
3. PersonaVLM: Long-Term Personalized Multimodal LLMs
https://huggingface.co/papers/2604.13074
4. Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems
https://huggingface.co/papers/2604.04936
5. Qwen3.5-Omni Technical Report
https://huggingface.co/papers/2604.15804]]>206ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-20--714708831. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
https://huggingface.co/papers/2604.14268
2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
https://huggingface.co/papers/2604.14683
3. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
https://huggingface.co/papers/2604.15308
4. How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
https://huggingface.co/papers/2604.14164
5. GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
https://huggingface.co/papers/2604.15284]]>https://api.spreaker.com/episode/71470883Sun, 19 Apr 2026 22:43:19 +0000ksterx【本日の論文】 1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://huggingface.co/papers/2604.14268 2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation...1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
https://huggingface.co/papers/2604.14268
2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
https://huggingface.co/papers/2604.14683
3. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
https://huggingface.co/papers/2604.15308
4. How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
https://huggingface.co/papers/2604.14164
5. GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
https://huggingface.co/papers/2604.15284]]>344ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-19--714437981. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
https://huggingface.co/papers/2604.14268
2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
https://huggingface.co/papers/2604.14683
3. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
https://huggingface.co/papers/2604.15308
4. How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
https://huggingface.co/papers/2604.14164
5. GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
https://huggingface.co/papers/2604.15284]]>https://api.spreaker.com/episode/71443798Sat, 18 Apr 2026 22:40:42 +0000ksterx【本日の論文】 1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://huggingface.co/papers/2604.14268 2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation...1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
https://huggingface.co/papers/2604.14268
2. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
https://huggingface.co/papers/2604.14683
3. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
https://huggingface.co/papers/2604.15308
4. How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
https://huggingface.co/papers/2604.14164
5. GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
https://huggingface.co/papers/2604.15284]]>232ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-18--714226511. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
https://huggingface.co/papers/2604.14268
2. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
https://huggingface.co/papers/2604.15308
3. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
https://huggingface.co/papers/2604.14683
4. How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
https://huggingface.co/papers/2604.14164
5. ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
https://huggingface.co/papers/2509.25843]]>https://api.spreaker.com/episode/71422651Fri, 17 Apr 2026 22:44:27 +0000ksterx【本日の論文】 1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://huggingface.co/papers/2604.14268 2. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework...1. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
https://huggingface.co/papers/2604.14268
2. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
https://huggingface.co/papers/2604.15308
3. DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
https://huggingface.co/papers/2604.14683
4. How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
https://huggingface.co/papers/2604.14164
5. ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
https://huggingface.co/papers/2509.25843]]>210ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-17--713846241. Seedance 2.0: Advancing Video Generation for World Complexity
https://huggingface.co/papers/2604.14148
2. GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
https://huggingface.co/papers/2604.07429
3. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
https://huggingface.co/papers/2604.11626
4. SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
https://huggingface.co/papers/2604.14144
5. OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
https://huggingface.co/papers/2604.10866]]>https://api.spreaker.com/episode/71384624Thu, 16 Apr 2026 22:45:28 +0000ksterx【本日の論文】 1. Seedance 2.0: Advancing Video Generation for World Complexity https://huggingface.co/papers/2604.14148 2. GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents https://huggingface.co/papers/2604.07429 3....1. Seedance 2.0: Advancing Video Generation for World Complexity
https://huggingface.co/papers/2604.14148
2. GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
https://huggingface.co/papers/2604.07429
3. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
https://huggingface.co/papers/2604.11626
4. SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
https://huggingface.co/papers/2604.14144
5. OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
https://huggingface.co/papers/2604.10866]]>184ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-16--713538751. ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
https://huggingface.co/papers/2604.11784
2. KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
https://huggingface.co/papers/2604.12627
3. Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
https://huggingface.co/papers/2604.13016
4. Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
https://huggingface.co/papers/2604.09574
5. SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
https://huggingface.co/papers/2604.08865]]>https://api.spreaker.com/episode/71353875Wed, 15 Apr 2026 22:48:34 +0000ksterx【本日の論文】 1. ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents https://huggingface.co/papers/2604.11784 2. KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance...1. ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
https://huggingface.co/papers/2604.11784
2. KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
https://huggingface.co/papers/2604.12627
3. Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
https://huggingface.co/papers/2604.13016
4. Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
https://huggingface.co/papers/2604.09574
5. SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
https://huggingface.co/papers/2604.08865]]>295ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-15--713302141. QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
https://huggingface.co/papers/2604.08570
2. The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
https://huggingface.co/papers/2604.11297
3. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
https://huggingface.co/papers/2604.11804
4. Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
https://huggingface.co/papers/2604.10098
5. Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
https://huggingface.co/papers/2604.09132]]>https://api.spreaker.com/episode/71330214Tue, 14 Apr 2026 22:50:36 +0000ksterx【本日の論文】 1. QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation https://huggingface.co/papers/2604.08570 2. The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping https://huggingface.co/papers/2604.11297 3....1. QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
https://huggingface.co/papers/2604.08570
2. The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
https://huggingface.co/papers/2604.11297
3. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
https://huggingface.co/papers/2604.11804
4. Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
https://huggingface.co/papers/2604.10098
5. Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
https://huggingface.co/papers/2604.09132]]>200ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-14--713007141. WildDet3D: Scaling Promptable 3D Detection in the Wild
https://huggingface.co/papers/2604.08626
2. FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios
https://huggingface.co/papers/2604.07413
3. RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
https://huggingface.co/papers/2604.06870
4. EXAONE 4.5 Technical Report
https://huggingface.co/papers/2604.08644
5. Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
https://huggingface.co/papers/2604.08995]]>https://api.spreaker.com/episode/71300714Mon, 13 Apr 2026 22:49:58 +0000ksterx【本日の論文】 1. WildDet3D: Scaling Promptable 3D Detection in the Wild https://huggingface.co/papers/2604.08626 2. FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios https://huggingface.co/papers/2604.07413 3. RefineAnything:...1. WildDet3D: Scaling Promptable 3D Detection in the Wild
https://huggingface.co/papers/2604.08626
2. FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios
https://huggingface.co/papers/2604.07413
3. RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
https://huggingface.co/papers/2604.06870
4. EXAONE 4.5 Technical Report
https://huggingface.co/papers/2604.08644
5. Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
https://huggingface.co/papers/2604.08995]]>272ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-13--712793931. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
https://huggingface.co/papers/2604.06628
2. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
https://huggingface.co/papers/2604.08377
3. ClawBench: Can AI Agents Complete Everyday Online Tasks?
https://huggingface.co/papers/2604.08523
4. HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
https://huggingface.co/papers/2604.07430
5. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
https://huggingface.co/papers/2604.08546]]>https://api.spreaker.com/episode/71279393Sun, 12 Apr 2026 22:41:03 +0000ksterx【本日の論文】 1. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability https://huggingface.co/papers/2604.06628 2. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver...1. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
https://huggingface.co/papers/2604.06628
2. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
https://huggingface.co/papers/2604.08377
3. ClawBench: Can AI Agents Complete Everyday Online Tasks?
https://huggingface.co/papers/2604.08523
4. HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
https://huggingface.co/papers/2604.07430
5. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
https://huggingface.co/papers/2604.08546]]>215ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-12--712648291. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
https://huggingface.co/papers/2604.08377
2. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
https://huggingface.co/papers/2604.06628
3. HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
https://huggingface.co/papers/2604.07430
4. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
https://huggingface.co/papers/2604.08546
5. ClawBench: Can AI Agents Complete Everyday Online Tasks?
https://huggingface.co/papers/2604.08523]]>https://api.spreaker.com/episode/71264829Sat, 11 Apr 2026 22:39:34 +0000ksterx【本日の論文】 1. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver https://huggingface.co/papers/2604.08377 2. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability...1. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
https://huggingface.co/papers/2604.08377
2. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
https://huggingface.co/papers/2604.06628
3. HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
https://huggingface.co/papers/2604.07430
4. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
https://huggingface.co/papers/2604.08546
5. ClawBench: Can AI Agents Complete Everyday Online Tasks?
https://huggingface.co/papers/2604.08523]]>244ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-11--712438871. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
https://huggingface.co/papers/2604.06628
2. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
https://huggingface.co/papers/2604.08377
3. HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
https://huggingface.co/papers/2604.07430
4. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
https://huggingface.co/papers/2604.08546
5. ClawBench: Can AI Agents Complete Everyday Online Tasks?
https://huggingface.co/papers/2604.08523]]>https://api.spreaker.com/episode/71243887Fri, 10 Apr 2026 22:43:09 +0000ksterx【本日の論文】 1. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability https://huggingface.co/papers/2604.06628 2. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver...1. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
https://huggingface.co/papers/2604.06628
2. SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
https://huggingface.co/papers/2604.08377
3. HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
https://huggingface.co/papers/2604.07430
4. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
https://huggingface.co/papers/2604.08546
5. ClawBench: Can AI Agents Complete Everyday Online Tasks?
https://huggingface.co/papers/2604.08523]]>177ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-10--712205311. Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
https://huggingface.co/papers/2604.04746
2. RAGEN-2: Reasoning Collapse in Agentic RL
https://huggingface.co/papers/2604.06268
3. MARS: Enabling Autoregressive Models Multi-Token Generation
https://huggingface.co/papers/2604.07023
4. Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
https://huggingface.co/papers/2604.04247
5. SEVerA: Verified Synthesis of Self-Evolving Agents
https://huggingface.co/papers/2603.25111]]>https://api.spreaker.com/episode/71220531Thu, 09 Apr 2026 22:46:48 +0000ksterx【本日の論文】 1. Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning https://huggingface.co/papers/2604.04746 2. RAGEN-2: Reasoning Collapse in Agentic RL https://huggingface.co/papers/2604.06268 3. MARS: Enabling...1. Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
https://huggingface.co/papers/2604.04746
2. RAGEN-2: Reasoning Collapse in Agentic RL
https://huggingface.co/papers/2604.06268
3. MARS: Enabling Autoregressive Models Multi-Token Generation
https://huggingface.co/papers/2604.07023
4. Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
https://huggingface.co/papers/2604.04247
5. SEVerA: Verified Synthesis of Self-Evolving Agents
https://huggingface.co/papers/2603.25111]]>207ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-09--711969451. Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
https://huggingface.co/papers/2604.05015
2. Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
https://huggingface.co/papers/2604.06132
3. Learning to Retrieve from Agent Trajectories
https://huggingface.co/papers/2604.04949
4. ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
https://huggingface.co/papers/2604.03922
5. GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
https://huggingface.co/papers/2604.02648]]>https://api.spreaker.com/episode/71196945Wed, 08 Apr 2026 22:45:27 +0000ksterx【本日の論文】 1. Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding https://huggingface.co/papers/2604.05015 2. Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents...1. Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
https://huggingface.co/papers/2604.05015
2. Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
https://huggingface.co/papers/2604.06132
3. Learning to Retrieve from Agent Trajectories
https://huggingface.co/papers/2604.04949
4. ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
https://huggingface.co/papers/2604.03922
5. GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
https://huggingface.co/papers/2604.02648]]>255ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-08--711681781. OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
https://huggingface.co/papers/2604.04707
2. MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
https://huggingface.co/papers/2604.04771
3. LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
https://huggingface.co/papers/2603.28301
4. TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
https://huggingface.co/papers/2604.04921
5. Adam's Law: Textual Frequency Law on Large Language Models
https://huggingface.co/papers/2604.02176]]>https://api.spreaker.com/episode/71168178Tue, 07 Apr 2026 22:43:36 +0000ksterx【本日の論文】 1. OpenWorldLib: A Unified Codebase and Definition of Advanced World Models https://huggingface.co/papers/2604.04707 2. MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale https://huggingface.co/papers/2604.04771...1. OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
https://huggingface.co/papers/2604.04707
2. MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
https://huggingface.co/papers/2604.04771
3. LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
https://huggingface.co/papers/2603.28301
4. TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
https://huggingface.co/papers/2604.04921
5. Adam's Law: Textual Frequency Law on Large Language Models
https://huggingface.co/papers/2604.02176]]>210ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-07--711418331. Self-Distilled RLVR
https://huggingface.co/papers/2604.03128
2. A Simple Baseline for Streaming Video Understanding
https://huggingface.co/papers/2604.02317
3. Token Warping Helps MLLMs Look from Nearby Viewpoints
https://huggingface.co/papers/2604.02870
4. Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
https://huggingface.co/papers/2604.03016
5. Test-Time Scaling Makes Overtraining Compute-Optimal
https://huggingface.co/papers/2604.01411]]>https://api.spreaker.com/episode/71141833Mon, 06 Apr 2026 22:43:37 +0000ksterx【本日の論文】 1. Self-Distilled RLVR https://huggingface.co/papers/2604.03128 2. A Simple Baseline for Streaming Video Understanding https://huggingface.co/papers/2604.02317 3. Token Warping Helps MLLMs Look from Nearby Viewpoints...1. Self-Distilled RLVR
https://huggingface.co/papers/2604.03128
2. A Simple Baseline for Streaming Video Understanding
https://huggingface.co/papers/2604.02317
3. Token Warping Helps MLLMs Look from Nearby Viewpoints
https://huggingface.co/papers/2604.02870
4. Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
https://huggingface.co/papers/2604.03016
5. Test-Time Scaling Makes Overtraining Compute-Optimal
https://huggingface.co/papers/2604.01411]]>304ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-06--711224121. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
https://huggingface.co/papers/2603.26164
2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
https://huggingface.co/papers/2604.02029
3. Generative World Renderer
https://huggingface.co/papers/2604.02329
4. SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
https://huggingface.co/papers/2604.02268
5. Steerable Visual Representations
https://huggingface.co/papers/2604.02327]]>https://api.spreaker.com/episode/71122412Sun, 05 Apr 2026 22:37:19 +0000ksterx【本日の論文】 1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models https://huggingface.co/papers/2603.26164 2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook...1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
https://huggingface.co/papers/2603.26164
2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
https://huggingface.co/papers/2604.02029
3. Generative World Renderer
https://huggingface.co/papers/2604.02329
4. SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
https://huggingface.co/papers/2604.02268
5. Steerable Visual Representations
https://huggingface.co/papers/2604.02327]]>248ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-05--711060581. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
https://huggingface.co/papers/2603.26164
2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
https://huggingface.co/papers/2604.02029
3. Generative World Renderer
https://huggingface.co/papers/2604.02329
4. SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
https://huggingface.co/papers/2604.02268
5. Steerable Visual Representations
https://huggingface.co/papers/2604.02327]]>https://api.spreaker.com/episode/71106058Sat, 04 Apr 2026 22:35:58 +0000ksterx【本日の論文】 1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models https://huggingface.co/papers/2603.26164 2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook...1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
https://huggingface.co/papers/2603.26164
2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
https://huggingface.co/papers/2604.02029
3. Generative World Renderer
https://huggingface.co/papers/2604.02329
4. SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
https://huggingface.co/papers/2604.02268
5. Steerable Visual Representations
https://huggingface.co/papers/2604.02327]]>188ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-04--710895191. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
https://huggingface.co/papers/2603.26164
2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
https://huggingface.co/papers/2604.02029
3. Generative World Renderer
https://huggingface.co/papers/2604.02329
4. SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
https://huggingface.co/papers/2604.02268
5. EgoSim: Egocentric World Simulator for Embodied Interaction Generation
https://huggingface.co/papers/2604.01001]]>https://api.spreaker.com/episode/71089519Fri, 03 Apr 2026 22:39:46 +0000ksterx【本日の論文】 1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models https://huggingface.co/papers/2603.26164 2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook...1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
https://huggingface.co/papers/2603.26164
2. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
https://huggingface.co/papers/2604.02029
3. Generative World Renderer
https://huggingface.co/papers/2604.02329
4. SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
https://huggingface.co/papers/2604.02268
5. EgoSim: Egocentric World Simulator for Embodied Interaction Generation
https://huggingface.co/papers/2604.01001]]>212ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-03--710724781. ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
https://huggingface.co/papers/2603.24414
2. Terminal Agents Suffice for Enterprise Automation
https://huggingface.co/papers/2604.00073
3. MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
https://huggingface.co/papers/2603.28407
4. ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
https://huggingface.co/papers/2603.25823
5. Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
https://huggingface.co/papers/2603.26648]]>https://api.spreaker.com/episode/71072478Thu, 02 Apr 2026 22:38:05 +0000ksterx【本日の論文】 1. ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers https://huggingface.co/papers/2603.24414 2. Terminal Agents Suffice for Enterprise Automation...1. ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
https://huggingface.co/papers/2603.24414
2. Terminal Agents Suffice for Enterprise Automation
https://huggingface.co/papers/2604.00073
3. MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
https://huggingface.co/papers/2603.28407
4. ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
https://huggingface.co/papers/2603.25823
5. Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
https://huggingface.co/papers/2603.26648]]>304ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-02--710520221. FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
https://huggingface.co/papers/2603.19835
2. CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
https://huggingface.co/papers/2603.28032
3. LongCat-Next: Lexicalizing Modalities as Discrete Tokens
https://huggingface.co/papers/2603.27538
4. Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
https://huggingface.co/papers/2603.25240
5. GEMS: Agent-Native Multimodal Generation with Memory and Skills
https://huggingface.co/papers/2603.28088]]>https://api.spreaker.com/episode/71052022Wed, 01 Apr 2026 22:44:04 +0000ksterx【本日の論文】 1. FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization https://huggingface.co/papers/2603.19835 2. CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence...1. FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
https://huggingface.co/papers/2603.19835
2. CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
https://huggingface.co/papers/2603.28032
3. LongCat-Next: Lexicalizing Modalities as Discrete Tokens
https://huggingface.co/papers/2603.27538
4. Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
https://huggingface.co/papers/2603.25240
5. GEMS: Agent-Native Multimodal Generation with Memory and Skills
https://huggingface.co/papers/2603.28088]]>269ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-04-01--710312171. TAPS: Task Aware Proposal Distributions for Speculative Sampling
https://huggingface.co/papers/2603.27027
2. Towards a Medical AI Scientist
https://huggingface.co/papers/2603.28589
3. Gen-Searcher: Reinforcing Agentic Search for Image Generation
https://huggingface.co/papers/2603.28767
4. Emergent Social Intelligence Risks in Generative Multi-Agent Systems
https://huggingface.co/papers/2603.27771
5. EpochX: Building the Infrastructure for an Emergent Agent Civilization
https://huggingface.co/papers/2603.27304]]>https://api.spreaker.com/episode/71031217Tue, 31 Mar 2026 22:40:42 +0000ksterx【本日の論文】 1. TAPS: Task Aware Proposal Distributions for Speculative Sampling https://huggingface.co/papers/2603.27027 2. Towards a Medical AI Scientist https://huggingface.co/papers/2603.28589 3. Gen-Searcher: Reinforcing Agentic Search for Image...1. TAPS: Task Aware Proposal Distributions for Speculative Sampling
https://huggingface.co/papers/2603.27027
2. Towards a Medical AI Scientist
https://huggingface.co/papers/2603.28589
3. Gen-Searcher: Reinforcing Agentic Search for Image Generation
https://huggingface.co/papers/2603.28767
4. Emergent Social Intelligence Risks in Generative Multi-Agent Systems
https://huggingface.co/papers/2603.27771
5. EpochX: Building the Infrastructure for an Emergent Agent Civilization
https://huggingface.co/papers/2603.27304]]>192ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-31--710077901. Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
https://huggingface.co/papers/2603.25716
2. ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
https://huggingface.co/papers/2603.25746
3. PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
https://huggingface.co/papers/2603.25730
4. Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
https://huggingface.co/papers/2603.25158
5. MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies
https://huggingface.co/papers/2603.24649]]>https://api.spreaker.com/episode/71007790Mon, 30 Mar 2026 22:41:21 +0000ksterx【本日の論文】 1. Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models https://huggingface.co/papers/2603.25716 2. ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling...1. Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
https://huggingface.co/papers/2603.25716
2. ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
https://huggingface.co/papers/2603.25746
3. PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
https://huggingface.co/papers/2603.25730
4. Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
https://huggingface.co/papers/2603.25158
5. MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies
https://huggingface.co/papers/2603.24649]]>229ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-30--709830561. PixelSmile: Toward Fine-Grained Facial Expression Editing
https://huggingface.co/papers/2603.25728
2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
https://huggingface.co/papers/2603.25040
3. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
https://huggingface.co/papers/2603.24800
4. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
https://huggingface.co/papers/2603.25502
5. Voxtral TTS
https://huggingface.co/papers/2603.25551]]>https://api.spreaker.com/episode/70983056Sun, 29 Mar 2026 22:38:11 +0000ksterx【本日の論文】 1. PixelSmile: Toward Fine-Grained Facial Expression Editing https://huggingface.co/papers/2603.25728 2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale https://huggingface.co/papers/2603.25040 3. Calibri:...1. PixelSmile: Toward Fine-Grained Facial Expression Editing
https://huggingface.co/papers/2603.25728
2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
https://huggingface.co/papers/2603.25040
3. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
https://huggingface.co/papers/2603.24800
4. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
https://huggingface.co/papers/2603.25502
5. Voxtral TTS
https://huggingface.co/papers/2603.25551]]>291ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-29--709625701. PixelSmile: Toward Fine-Grained Facial Expression Editing
https://huggingface.co/papers/2603.25728
2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
https://huggingface.co/papers/2603.25040
3. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
https://huggingface.co/papers/2603.24800
4. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
https://huggingface.co/papers/2603.25502
5. Voxtral TTS
https://huggingface.co/papers/2603.25551]]>https://api.spreaker.com/episode/70962570Sat, 28 Mar 2026 22:34:46 +0000ksterx【本日の論文】 1. PixelSmile: Toward Fine-Grained Facial Expression Editing https://huggingface.co/papers/2603.25728 2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale https://huggingface.co/papers/2603.25040 3. Calibri:...1. PixelSmile: Toward Fine-Grained Facial Expression Editing
https://huggingface.co/papers/2603.25728
2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
https://huggingface.co/papers/2603.25040
3. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
https://huggingface.co/papers/2603.24800
4. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
https://huggingface.co/papers/2603.25502
5. Voxtral TTS
https://huggingface.co/papers/2603.25551]]>181ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-28--709404991. PixelSmile: Toward Fine-Grained Facial Expression Editing
https://huggingface.co/papers/2603.25728
2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
https://huggingface.co/papers/2603.25040
3. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
https://huggingface.co/papers/2603.25502
4. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
https://huggingface.co/papers/2603.24800
5. MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
https://huggingface.co/papers/2603.25319]]>https://api.spreaker.com/episode/70940499Fri, 27 Mar 2026 22:38:29 +0000ksterx【本日の論文】 1. PixelSmile: Toward Fine-Grained Facial Expression Editing https://huggingface.co/papers/2603.25728 2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale https://huggingface.co/papers/2603.25040 3. RealRestorer:...1. PixelSmile: Toward Fine-Grained Facial Expression Editing
https://huggingface.co/papers/2603.25728
2. Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
https://huggingface.co/papers/2603.25040
3. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
https://huggingface.co/papers/2603.25502
4. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
https://huggingface.co/papers/2603.24800
5. MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
https://huggingface.co/papers/2603.25319]]>215ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-27--709074451. CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
https://huggingface.co/papers/2603.24440
2. EVA: Efficient Reinforcement Learning for End-to-End Video Agent
https://huggingface.co/papers/2603.22918
3. UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
https://huggingface.co/papers/2603.24533
4. T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
https://huggingface.co/papers/2603.22341
5. Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
https://huggingface.co/papers/2603.24472]]>https://api.spreaker.com/episode/70907445Thu, 26 Mar 2026 22:35:50 +0000ksterx【本日の論文】 1. CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents https://huggingface.co/papers/2603.24440 2. EVA: Efficient Reinforcement Learning for End-to-End Video Agent https://huggingface.co/papers/2603.22918 3....1. CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
https://huggingface.co/papers/2603.24440
2. EVA: Efficient Reinforcement Learning for End-to-End Video Agent
https://huggingface.co/papers/2603.22918
3. UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
https://huggingface.co/papers/2603.24533
4. T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
https://huggingface.co/papers/2603.22341
5. Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
https://huggingface.co/papers/2603.24472]]>204ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-26--708806731. MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
https://huggingface.co/papers/2603.22458
2. WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
https://huggingface.co/papers/2603.23497
3. SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
https://huggingface.co/papers/2603.23483
4. From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
https://huggingface.co/papers/2603.22386
5. PEARL: Personalized Streaming Video Understanding Model
https://huggingface.co/papers/2603.20422]]>https://api.spreaker.com/episode/70880673Wed, 25 Mar 2026 22:41:19 +0000ksterx【本日の論文】 1. MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding https://huggingface.co/papers/2603.22458 2. WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward...1. MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
https://huggingface.co/papers/2603.22458
2. WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
https://huggingface.co/papers/2603.23497
3. SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
https://huggingface.co/papers/2603.23483
4. From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
https://huggingface.co/papers/2603.22386
5. PEARL: Personalized Streaming Video Understanding Model
https://huggingface.co/papers/2603.20422]]>173ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-25--708603741. Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
https://huggingface.co/papers/2603.22212
2. Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
https://huggingface.co/papers/2603.21986
3. LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
https://huggingface.co/papers/2603.21065
4. Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
https://huggingface.co/papers/2603.16932
5. OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
https://huggingface.co/papers/2603.20278]]>https://api.spreaker.com/episode/70860374Tue, 24 Mar 2026 22:37:24 +0000ksterx【本日の論文】 1. Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models https://huggingface.co/papers/2603.22212 2. Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model...1. Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
https://huggingface.co/papers/2603.22212
2. Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
https://huggingface.co/papers/2603.21986
3. LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
https://huggingface.co/papers/2603.21065
4. Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
https://huggingface.co/papers/2603.16932
5. OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
https://huggingface.co/papers/2603.20278]]>198ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-24--708398661. HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
https://huggingface.co/papers/2603.17024
2. Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
https://huggingface.co/papers/2603.17051
3. TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
https://huggingface.co/papers/2603.19039
4. ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
https://huggingface.co/papers/2603.19466
5. FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow
https://huggingface.co/papers/2603.19598]]>https://api.spreaker.com/episode/70839866Mon, 23 Mar 2026 22:37:55 +0000ksterx【本日の論文】 1. HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning https://huggingface.co/papers/2603.17024 2. Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models...1. HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
https://huggingface.co/papers/2603.17024
2. Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
https://huggingface.co/papers/2603.17051
3. TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
https://huggingface.co/papers/2603.19039
4. ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
https://huggingface.co/papers/2603.19466
5. FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow
https://huggingface.co/papers/2603.19598]]>212ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-23--708177831. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
https://huggingface.co/papers/2603.19235
2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
https://huggingface.co/papers/2603.19228
3. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
https://huggingface.co/papers/2603.18524
4. FASTER: Rethinking Real-Time Flow VLAs
https://huggingface.co/papers/2603.19199
5. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
https://huggingface.co/papers/2603.19220]]>https://api.spreaker.com/episode/70817783Sun, 22 Mar 2026 22:30:40 +0000ksterx【本日の論文】 1. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding https://huggingface.co/papers/2603.19235 2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing...1. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
https://huggingface.co/papers/2603.19235
2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
https://huggingface.co/papers/2603.19228
3. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
https://huggingface.co/papers/2603.18524
4. FASTER: Rethinking Real-Time Flow VLAs
https://huggingface.co/papers/2603.19199
5. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
https://huggingface.co/papers/2603.19220]]>188ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-22--708035391. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
https://huggingface.co/papers/2603.19235
2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
https://huggingface.co/papers/2603.19228
3. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
https://huggingface.co/papers/2603.18524
4. FASTER: Rethinking Real-Time Flow VLAs
https://huggingface.co/papers/2603.19199
5. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
https://huggingface.co/papers/2603.19220]]>https://api.spreaker.com/episode/70803539Sat, 21 Mar 2026 22:31:48 +0000ksterx【本日の論文】 1. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding https://huggingface.co/papers/2603.19235 2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing...1. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
https://huggingface.co/papers/2603.19235
2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
https://huggingface.co/papers/2603.19228
3. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
https://huggingface.co/papers/2603.18524
4. FASTER: Rethinking Real-Time Flow VLAs
https://huggingface.co/papers/2603.19199
5. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
https://huggingface.co/papers/2603.19220]]>299ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-21--707881111. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
https://huggingface.co/papers/2603.19235
2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
https://huggingface.co/papers/2603.19228
3. FASTER: Rethinking Real-Time Flow VLAs
https://huggingface.co/papers/2603.19199
4. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
https://huggingface.co/papers/2603.18524
5. Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
https://huggingface.co/papers/2603.19227]]>https://api.spreaker.com/episode/70788111Fri, 20 Mar 2026 22:35:22 +0000ksterx【本日の論文】 1. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding https://huggingface.co/papers/2603.19235 2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing...1. Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
https://huggingface.co/papers/2603.19235
2. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
https://huggingface.co/papers/2603.19228
3. FASTER: Rethinking Real-Time Flow VLAs
https://huggingface.co/papers/2603.19199
4. 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
https://huggingface.co/papers/2603.18524
5. Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
https://huggingface.co/papers/2603.19227]]>368ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-20--707663051. MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
https://huggingface.co/papers/2603.17187
2. Video-CoE: Reinforcing Video Event Prediction via Chain of Events
https://huggingface.co/papers/2603.14935
3. MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
https://huggingface.co/papers/2603.17117
4. Alignment Makes Language Models Normative, Not Descriptive
https://huggingface.co/papers/2603.17218
5. Complementary Reinforcement Learning
https://huggingface.co/papers/2603.17621]]>https://api.spreaker.com/episode/70766305Thu, 19 Mar 2026 22:33:10 +0000ksterx【本日の論文】 1. MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild https://huggingface.co/papers/2603.17187 2. Video-CoE: Reinforcing Video Event Prediction via Chain of Events https://huggingface.co/papers/2603.14935 3....1. MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
https://huggingface.co/papers/2603.17187
2. Video-CoE: Reinforcing Video Event Prediction via Chain of Events
https://huggingface.co/papers/2603.14935
3. MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
https://huggingface.co/papers/2603.17117
4. Alignment Makes Language Models Normative, Not Descriptive
https://huggingface.co/papers/2603.17218
5. Complementary Reinforcement Learning
https://huggingface.co/papers/2603.17621]]>197ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-19--707273201. InCoder-32B: Code Foundation Model for Industrial Scenarios
https://huggingface.co/papers/2603.16790
2. MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
https://huggingface.co/papers/2603.15726
3. Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
https://huggingface.co/papers/2603.13398
4. Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
https://huggingface.co/papers/2603.16669
5. Demystifing Video Reasoning
https://huggingface.co/papers/2603.16870]]>https://api.spreaker.com/episode/70727320Wed, 18 Mar 2026 22:38:03 +0000ksterx【本日の論文】 1. InCoder-32B: Code Foundation Model for Industrial Scenarios https://huggingface.co/papers/2603.16790 2. MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification https://huggingface.co/papers/2603.15726 3. Qianfan-OCR:...1. InCoder-32B: Code Foundation Model for Industrial Scenarios
https://huggingface.co/papers/2603.16790
2. MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
https://huggingface.co/papers/2603.15726
3. Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
https://huggingface.co/papers/2603.13398
4. Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
https://huggingface.co/papers/2603.16669
5. Demystifing Video Reasoning
https://huggingface.co/papers/2603.16870]]>188ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-18--707008491. AI Can Learn Scientific Taste
https://huggingface.co/papers/2603.14473
2. OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
https://huggingface.co/papers/2603.15594
3. EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
https://huggingface.co/papers/2603.13594
4. HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions
https://huggingface.co/papers/2603.15612
5. Grounding World Simulation Models in a Real-World Metropolis
https://huggingface.co/papers/2603.15583]]>https://api.spreaker.com/episode/70700849Tue, 17 Mar 2026 22:56:58 +0000ksterx【本日の論文】 1. AI Can Learn Scientific Taste https://huggingface.co/papers/2603.14473 2. OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data https://huggingface.co/papers/2603.15594 3. EnterpriseOps-Gym:...1. AI Can Learn Scientific Taste
https://huggingface.co/papers/2603.14473
2. OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
https://huggingface.co/papers/2603.15594
3. EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
https://huggingface.co/papers/2603.13594
4. HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions
https://huggingface.co/papers/2603.15612
5. Grounding World Simulation Models in a Real-World Metropolis
https://huggingface.co/papers/2603.15583]]>221ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-17--706699311. LMEB: Long-horizon Memory Embedding Benchmark
https://huggingface.co/papers/2603.12572
2. Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
https://huggingface.co/papers/2603.12793
3. Can Vision-Language Models Solve the Shell Game?
https://huggingface.co/papers/2603.08436
4. daVinci-Env: Open SWE Environment Synthesis at Scale
https://huggingface.co/papers/2603.13023
5. OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
https://huggingface.co/papers/2603.11647]]>https://api.spreaker.com/episode/70669931Mon, 16 Mar 2026 22:39:51 +0000ksterx【本日の論文】 1. LMEB: Long-horizon Memory Embedding Benchmark https://huggingface.co/papers/2603.12572 2. Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation...1. LMEB: Long-horizon Memory Embedding Benchmark
https://huggingface.co/papers/2603.12572
2. Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
https://huggingface.co/papers/2603.12793
3. Can Vision-Language Models Solve the Shell Game?
https://huggingface.co/papers/2603.08436
4. daVinci-Env: Open SWE Environment Synthesis at Scale
https://huggingface.co/papers/2603.13023
5. OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
https://huggingface.co/papers/2603.11647]]>227ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-16--706507981. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
https://huggingface.co/papers/2603.12255
2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
https://huggingface.co/papers/2603.12180
3. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
https://huggingface.co/papers/2603.12201
4. Video-Based Reward Modeling for Computer-Use Agents
https://huggingface.co/papers/2603.10178
5. ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
https://huggingface.co/papers/2603.11421]]>https://api.spreaker.com/episode/70650798Sun, 15 Mar 2026 22:36:09 +0000ksterx【本日の論文】 1. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training https://huggingface.co/papers/2603.12255 2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections...1. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
https://huggingface.co/papers/2603.12255
2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
https://huggingface.co/papers/2603.12180
3. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
https://huggingface.co/papers/2603.12201
4. Video-Based Reward Modeling for Computer-Use Agents
https://huggingface.co/papers/2603.10178
5. ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
https://huggingface.co/papers/2603.11421]]>298ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-15--706397801. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
https://huggingface.co/papers/2603.12255
2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
https://huggingface.co/papers/2603.12180
3. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
https://huggingface.co/papers/2603.12201
4. Video-Based Reward Modeling for Computer-Use Agents
https://huggingface.co/papers/2603.10178
5. ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
https://huggingface.co/papers/2603.11421]]>https://api.spreaker.com/episode/70639780Sat, 14 Mar 2026 22:32:47 +0000ksterx【本日の論文】 1. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training https://huggingface.co/papers/2603.12255 2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections...1. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
https://huggingface.co/papers/2603.12255
2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
https://huggingface.co/papers/2603.12180
3. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
https://huggingface.co/papers/2603.12201
4. Video-Based Reward Modeling for Computer-Use Agents
https://huggingface.co/papers/2603.10178
5. ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
https://huggingface.co/papers/2603.11421]]>260ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-14--706295841. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
https://huggingface.co/papers/2603.12255
2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
https://huggingface.co/papers/2603.12180
3. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
https://huggingface.co/papers/2603.12201
4. Video-Based Reward Modeling for Computer-Use Agents
https://huggingface.co/papers/2603.10178
5. DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning
https://huggingface.co/papers/2603.12257]]>https://api.spreaker.com/episode/70629584Fri, 13 Mar 2026 22:35:01 +0000ksterx【本日の論文】 1. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training https://huggingface.co/papers/2603.12255 2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections...1. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
https://huggingface.co/papers/2603.12255
2. Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
https://huggingface.co/papers/2603.12180
3. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
https://huggingface.co/papers/2603.12201
4. Video-Based Reward Modeling for Computer-Use Agents
https://huggingface.co/papers/2603.10178
5. DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning
https://huggingface.co/papers/2603.12257]]>292ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-13--706146821. OpenClaw-RL: Train Any Agent Simply by Talking
https://huggingface.co/papers/2603.10165
2. Flash-KMeans: Fast and Memory-Efficient Exact K-Means
https://huggingface.co/papers/2603.09229
3. MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
https://huggingface.co/papers/2603.09827
4. LLM2Vec-Gen: Generative Embeddings from Large Language Models
https://huggingface.co/papers/2603.10913
5. ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
https://huggingface.co/papers/2603.10160]]>https://api.spreaker.com/episode/70614682Thu, 12 Mar 2026 22:32:39 +0000ksterx【本日の論文】 1. OpenClaw-RL: Train Any Agent Simply by Talking https://huggingface.co/papers/2603.10165 2. Flash-KMeans: Fast and Memory-Efficient Exact K-Means https://huggingface.co/papers/2603.09229 3. MA-EgoQA: Question Answering over Egocentric...1. OpenClaw-RL: Train Any Agent Simply by Talking
https://huggingface.co/papers/2603.10165
2. Flash-KMeans: Fast and Memory-Efficient Exact K-Means
https://huggingface.co/papers/2603.09229
3. MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
https://huggingface.co/papers/2603.09827
4. LLM2Vec-Gen: Generative Embeddings from Large Language Models
https://huggingface.co/papers/2603.10913
5. ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
https://huggingface.co/papers/2603.10160]]>240ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-12--706006601. Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing
https://huggingface.co/papers/2603.03143
2. Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
https://huggingface.co/papers/2603.09906
3. Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
https://huggingface.co/papers/2603.06577
4. MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
https://huggingface.co/papers/2603.09206
5. InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
https://huggingface.co/papers/2603.09877]]>https://api.spreaker.com/episode/70600660Wed, 11 Mar 2026 22:32:48 +0000ksterx【本日の論文】 1. Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing https://huggingface.co/papers/2603.03143 2. Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs...1. Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing
https://huggingface.co/papers/2603.03143
2. Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
https://huggingface.co/papers/2603.09906
3. Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
https://huggingface.co/papers/2603.06577
4. MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
https://huggingface.co/papers/2603.09206
5. InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
https://huggingface.co/papers/2603.09877]]>245ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-11--705807191. Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
https://huggingface.co/papers/2603.05890
2. Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
https://huggingface.co/papers/2603.07660
3. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
https://huggingface.co/papers/2603.03269
4. Believe Your Model: Distribution-Guided Confidence Calibration
https://huggingface.co/papers/2603.03872
5. How Far Can Unsupervised RLVR Scale LLM Training?
https://huggingface.co/papers/2603.08660]]>https://api.spreaker.com/episode/70580719Tue, 10 Mar 2026 22:36:13 +0000ksterx【本日の論文】 1. Lost in Stories: Consistency Bugs in Long Story Generation by LLMs https://huggingface.co/papers/2603.05890 2. Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence https://huggingface.co/papers/2603.07660 3....1. Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
https://huggingface.co/papers/2603.05890
2. Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
https://huggingface.co/papers/2603.07660
3. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
https://huggingface.co/papers/2603.03269
4. Believe Your Model: Distribution-Guided Confidence Calibration
https://huggingface.co/papers/2603.03872
5. How Far Can Unsupervised RLVR Scale LLM Training?
https://huggingface.co/papers/2603.08660]]>306ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-10--705564051. Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
https://huggingface.co/papers/2603.06569
2. BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
https://huggingface.co/papers/2603.04918
3. Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
https://huggingface.co/papers/2603.05438
4. WildActor: Unconstrained Identity-Preserving Video Generation
https://huggingface.co/papers/2603.00586
5. Progressive Residual Warmup for Language Model Pretraining
https://huggingface.co/papers/2603.05369]]>https://api.spreaker.com/episode/70556405Mon, 09 Mar 2026 22:36:20 +0000ksterx【本日の論文】 1. Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders https://huggingface.co/papers/2603.06569 2. BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning...1. Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
https://huggingface.co/papers/2603.06569
2. BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
https://huggingface.co/papers/2603.04918
3. Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
https://huggingface.co/papers/2603.05438
4. WildActor: Unconstrained Identity-Preserving Video Generation
https://huggingface.co/papers/2603.00586
5. Progressive Residual Warmup for Language Model Pretraining
https://huggingface.co/papers/2603.05369]]>282ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-09--705412871. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
https://huggingface.co/papers/2603.03756
2. SkillNet: Create, Evaluate, and Connect AI Skills
https://huggingface.co/papers/2603.04448
3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
https://huggingface.co/papers/2603.04743
4. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
https://huggingface.co/papers/2602.23166
5. RoboPocket: Improve Robot Policies Instantly with Your Phone
https://huggingface.co/papers/2603.05504]]>https://api.spreaker.com/episode/70541287Sun, 08 Mar 2026 22:28:55 +0000ksterx【本日の論文】 1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier https://huggingface.co/papers/2603.03756 2. SkillNet: Create, Evaluate, and Connect AI Skills...1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
https://huggingface.co/papers/2603.03756
2. SkillNet: Create, Evaluate, and Connect AI Skills
https://huggingface.co/papers/2603.04448
3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
https://huggingface.co/papers/2603.04743
4. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
https://huggingface.co/papers/2602.23166
5. RoboPocket: Improve Robot Policies Instantly with Your Phone
https://huggingface.co/papers/2603.05504]]>223ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-08--705294351. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
https://huggingface.co/papers/2603.03756
2. SkillNet: Create, Evaluate, and Connect AI Skills
https://huggingface.co/papers/2603.04448
3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
https://huggingface.co/papers/2603.04743
4. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
https://huggingface.co/papers/2602.23166
5. RoboPocket: Improve Robot Policies Instantly with Your Phone
https://huggingface.co/papers/2603.05504]]>https://api.spreaker.com/episode/70529435Sat, 07 Mar 2026 22:29:55 +0000ksterx【本日の論文】 1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier https://huggingface.co/papers/2603.03756 2. SkillNet: Create, Evaluate, and Connect AI Skills...1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
https://huggingface.co/papers/2603.03756
2. SkillNet: Create, Evaluate, and Connect AI Skills
https://huggingface.co/papers/2603.04448
3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
https://huggingface.co/papers/2603.04743
4. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
https://huggingface.co/papers/2602.23166
5. RoboPocket: Improve Robot Policies Instantly with Your Phone
https://huggingface.co/papers/2603.05504]]>308ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-07--705161981. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
https://huggingface.co/papers/2603.03756
2. SkillNet: Create, Evaluate, and Connect AI Skills
https://huggingface.co/papers/2603.04448
3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
https://huggingface.co/papers/2603.04743
4. RoboPocket: Improve Robot Policies Instantly with Your Phone
https://huggingface.co/papers/2603.05504
5. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
https://huggingface.co/papers/2602.23166]]>https://api.spreaker.com/episode/70516198Fri, 06 Mar 2026 22:34:17 +0000ksterx【本日の論文】 1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier https://huggingface.co/papers/2603.03756 2. SkillNet: Create, Evaluate, and Connect AI Skills...1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
https://huggingface.co/papers/2603.03756
2. SkillNet: Create, Evaluate, and Connect AI Skills
https://huggingface.co/papers/2603.04448
3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
https://huggingface.co/papers/2603.04743
4. RoboPocket: Improve Robot Policies Instantly with Your Phone
https://huggingface.co/papers/2603.05504
5. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
https://huggingface.co/papers/2602.23166]]>212ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-06--704923991. Helios: Real Real-Time Long Video Generation Model
https://huggingface.co/papers/2603.04379
2. T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning
https://huggingface.co/papers/2603.03790
3. Heterogeneous Agent Collaborative Reinforcement Learning
https://huggingface.co/papers/2603.02604
4. Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
https://huggingface.co/papers/2603.03447
5. MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
https://huggingface.co/papers/2603.03379]]>https://api.spreaker.com/episode/70492399Thu, 05 Mar 2026 22:37:44 +0000ksterx【本日の論文】 1. Helios: Real Real-Time Long Video Generation Model https://huggingface.co/papers/2603.04379 2. T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning...1. Helios: Real Real-Time Long Video Generation Model
https://huggingface.co/papers/2603.04379
2. T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning
https://huggingface.co/papers/2603.03790
3. Heterogeneous Agent Collaborative Reinforcement Learning
https://huggingface.co/papers/2603.02604
4. Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
https://huggingface.co/papers/2603.03447
5. MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
https://huggingface.co/papers/2603.03379]]>182ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-05--704580431. Utonia: Toward One Encoder for All Point Clouds
https://huggingface.co/papers/2603.03283
2. UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
https://huggingface.co/papers/2603.03241
3. Beyond Language Modeling: An Exploration of Multimodal Pretraining
https://huggingface.co/papers/2603.03276
4. BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
https://huggingface.co/papers/2603.03194
5. Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
https://huggingface.co/papers/2603.01571]]>https://api.spreaker.com/episode/70458043Wed, 04 Mar 2026 22:36:14 +0000ksterx【本日の論文】 1. Utonia: Toward One Encoder for All Point Clouds https://huggingface.co/papers/2603.03283 2. UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? https://huggingface.co/papers/2603.03241 3. Beyond Language Modeling: An...1. Utonia: Toward One Encoder for All Point Clouds
https://huggingface.co/papers/2603.03283
2. UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
https://huggingface.co/papers/2603.03241
3. Beyond Language Modeling: An Exploration of Multimodal Pretraining
https://huggingface.co/papers/2603.03276
4. BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
https://huggingface.co/papers/2603.03194
5. Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
https://huggingface.co/papers/2603.01571]]>177ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-04--704273141. From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
https://huggingface.co/papers/2603.00141
2. OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
https://huggingface.co/papers/2603.02138
3. SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
https://huggingface.co/papers/2602.23866
4. RubricBench: Aligning Model-Generated Rubrics with Human Standards
https://huggingface.co/papers/2603.01562
5. OpenAutoNLU: Open Source AutoML Library for NLU
https://huggingface.co/papers/2603.01824]]>https://api.spreaker.com/episode/70427314Tue, 03 Mar 2026 22:35:37 +0000ksterx【本日の論文】 1. From Scale to Speed: Adaptive Test-Time Scaling for Image Editing https://huggingface.co/papers/2603.00141 2. OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens https://huggingface.co/papers/2603.02138 3....1. From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
https://huggingface.co/papers/2603.00141
2. OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
https://huggingface.co/papers/2603.02138
3. SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
https://huggingface.co/papers/2602.23866
4. RubricBench: Aligning Model-Generated Rubrics with Human Standards
https://huggingface.co/papers/2603.01562
5. OpenAutoNLU: Open Source AutoML Library for NLU
https://huggingface.co/papers/2603.01824]]>213ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-03--703981241. dLLM: Simple Diffusion Language Modeling
https://huggingface.co/papers/2602.22661
2. Enhancing Spatial Understanding in Image Generation via Reward Modeling
https://huggingface.co/papers/2602.24233
3. Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
https://huggingface.co/papers/2602.22207
4. CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
https://huggingface.co/papers/2602.24286
5. Mode Seeking meets Mean Seeking for Fast Long Video Generation
https://huggingface.co/papers/2602.24289]]>https://api.spreaker.com/episode/70398124Mon, 02 Mar 2026 22:33:45 +0000ksterx【本日の論文】 1. dLLM: Simple Diffusion Language Modeling https://huggingface.co/papers/2602.22661 2. Enhancing Spatial Understanding in Image Generation via Reward Modeling https://huggingface.co/papers/2602.24233 3. Recovered in Translation:...1. dLLM: Simple Diffusion Language Modeling
https://huggingface.co/papers/2602.22661
2. Enhancing Spatial Understanding in Image Generation via Reward Modeling
https://huggingface.co/papers/2602.24233
3. Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
https://huggingface.co/papers/2602.22207
4. CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
https://huggingface.co/papers/2602.24286
5. Mode Seeking meets Mean Seeking for Fast Long Video Generation
https://huggingface.co/papers/2602.24289]]>195ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-02--703793181. The Trinity of Consistency as a Defining Principle for General World Models
https://huggingface.co/papers/2602.23152
2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
https://huggingface.co/papers/2602.22859
3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
https://huggingface.co/papers/2602.22638
4. OmniGAIA: Towards Native Omni-Modal AI Agents
https://huggingface.co/papers/2602.22897
5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space
https://huggingface.co/papers/2602.22766]]>https://api.spreaker.com/episode/70379318Sun, 01 Mar 2026 22:30:14 +0000ksterx【本日の論文】 1. The Trinity of Consistency as a Defining Principle for General World Models https://huggingface.co/papers/2602.23152 2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models...1. The Trinity of Consistency as a Defining Principle for General World Models
https://huggingface.co/papers/2602.23152
2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
https://huggingface.co/papers/2602.22859
3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
https://huggingface.co/papers/2602.22638
4. OmniGAIA: Towards Native Omni-Modal AI Agents
https://huggingface.co/papers/2602.22897
5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space
https://huggingface.co/papers/2602.22766]]>214ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-03-01--703667691. The Trinity of Consistency as a Defining Principle for General World Models
https://huggingface.co/papers/2602.23152
2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
https://huggingface.co/papers/2602.22859
3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
https://huggingface.co/papers/2602.22638
4. OmniGAIA: Towards Native Omni-Modal AI Agents
https://huggingface.co/papers/2602.22897
5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space
https://huggingface.co/papers/2602.22766]]>https://api.spreaker.com/episode/70366769Sat, 28 Feb 2026 22:28:44 +0000ksterx【本日の論文】 1. The Trinity of Consistency as a Defining Principle for General World Models https://huggingface.co/papers/2602.23152 2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models...1. The Trinity of Consistency as a Defining Principle for General World Models
https://huggingface.co/papers/2602.23152
2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
https://huggingface.co/papers/2602.22859
3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
https://huggingface.co/papers/2602.22638
4. OmniGAIA: Towards Native Omni-Modal AI Agents
https://huggingface.co/papers/2602.22897
5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space
https://huggingface.co/papers/2602.22766]]>210ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-28--703482601. The Trinity of Consistency as a Defining Principle for General World Models
https://huggingface.co/papers/2602.23152
2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
https://huggingface.co/papers/2602.22859
3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
https://huggingface.co/papers/2602.22638
4. OmniGAIA: Towards Native Omni-Modal AI Agents
https://huggingface.co/papers/2602.22897
5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space
https://huggingface.co/papers/2602.22766]]>https://api.spreaker.com/episode/70348260Fri, 27 Feb 2026 22:28:47 +0000ksterx【本日の論文】 1. The Trinity of Consistency as a Defining Principle for General World Models https://huggingface.co/papers/2602.23152 2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models...1. The Trinity of Consistency as a Defining Principle for General World Models
https://huggingface.co/papers/2602.23152
2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
https://huggingface.co/papers/2602.22859
3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
https://huggingface.co/papers/2602.22638
4. OmniGAIA: Towards Native Omni-Modal AI Agents
https://huggingface.co/papers/2602.22897
5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space
https://huggingface.co/papers/2602.22766]]>223ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-27--703094981. HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation
https://huggingface.co/papers/2602.18283
2. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
https://huggingface.co/papers/2602.17602
3. DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
https://huggingface.co/papers/2602.12160
4. SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model
https://huggingface.co/papers/2602.21818
5. ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
https://huggingface.co/papers/2602.21534]]>https://api.spreaker.com/episode/70309498Thu, 26 Feb 2026 22:38:56 +0000ksterx【本日の論文】 1. HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation https://huggingface.co/papers/2602.18283 2. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models...1. HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation
https://huggingface.co/papers/2602.18283
2. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
https://huggingface.co/papers/2602.17602
3. DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
https://huggingface.co/papers/2602.12160
4. SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model
https://huggingface.co/papers/2602.21818
5. ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
https://huggingface.co/papers/2602.21534]]>193ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-26--702815101. On Data Engineering for Scaling LLM Terminal Capabilities
https://huggingface.co/papers/2602.21193
2. Query-focused and Memory-aware Reranker for Long Context Processing
https://huggingface.co/papers/2602.12192
3. PyVision-RL: Forging Open Agentic Vision Models via RL
https://huggingface.co/papers/2602.20739
4. From Perception to Action: An Interactive Benchmark for Vision Reasoning
https://huggingface.co/papers/2602.21015
5. Test-Time Training with KV Binding Is Secretly Linear Attention
https://huggingface.co/papers/2602.21204]]>https://api.spreaker.com/episode/70281510Wed, 25 Feb 2026 22:39:31 +0000ksterx【本日の論文】 1. On Data Engineering for Scaling LLM Terminal Capabilities https://huggingface.co/papers/2602.21193 2. Query-focused and Memory-aware Reranker for Long Context Processing https://huggingface.co/papers/2602.12192 3. PyVision-RL: Forging...1. On Data Engineering for Scaling LLM Terminal Capabilities
https://huggingface.co/papers/2602.21193
2. Query-focused and Memory-aware Reranker for Long Context Processing
https://huggingface.co/papers/2602.12192
3. PyVision-RL: Forging Open Agentic Vision Models via RL
https://huggingface.co/papers/2602.20739
4. From Perception to Action: An Interactive Benchmark for Vision Reasoning
https://huggingface.co/papers/2602.21015
5. Test-Time Training with KV Binding Is Secretly Linear Attention
https://huggingface.co/papers/2602.21204]]>177ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-25--702579301. A Very Big Video Reasoning Suite
https://huggingface.co/papers/2602.20159
2. VLANeXt: Recipes for Building Strong VLA Models
https://huggingface.co/papers/2602.18532
3. SkillOrchestra: Learning to Route Agents via Skill Transfer
https://huggingface.co/papers/2602.19672
4. TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
https://huggingface.co/papers/2602.19313
5. Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device
https://huggingface.co/papers/2602.20161]]>https://api.spreaker.com/episode/70257930Tue, 24 Feb 2026 22:41:09 +0000ksterx【本日の論文】 1. A Very Big Video Reasoning Suite https://huggingface.co/papers/2602.20159 2. VLANeXt: Recipes for Building Strong VLA Models https://huggingface.co/papers/2602.18532 3. SkillOrchestra: Learning to Route Agents via Skill Transfer...1. A Very Big Video Reasoning Suite
https://huggingface.co/papers/2602.20159
2. VLANeXt: Recipes for Building Strong VLA Models
https://huggingface.co/papers/2602.18532
3. SkillOrchestra: Learning to Route Agents via Skill Transfer
https://huggingface.co/papers/2602.19672
4. TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
https://huggingface.co/papers/2602.19313
5. Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device
https://huggingface.co/papers/2602.20161]]>325ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-24--702419841. VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
https://huggingface.co/papers/2602.10693
2. Does Your Reasoning Model Implicitly Know When to Stop Thinking?
https://huggingface.co/papers/2602.08354
3. Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
https://huggingface.co/papers/2602.18422
4. Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
https://huggingface.co/papers/2602.18292
5. Spanning the Visual Analogy Space with a Weight Basis of LoRAs
https://huggingface.co/papers/2602.15727]]>https://api.spreaker.com/episode/70241984Mon, 23 Feb 2026 22:47:38 +0000ksterx【本日の論文】 1. VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training https://huggingface.co/papers/2602.10693 2. Does Your Reasoning Model Implicitly Know When to Stop Thinking?...1. VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
https://huggingface.co/papers/2602.10693
2. Does Your Reasoning Model Implicitly Know When to Stop Thinking?
https://huggingface.co/papers/2602.08354
3. Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
https://huggingface.co/papers/2602.18422
4. Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
https://huggingface.co/papers/2602.18292
5. Spanning the Visual Analogy Space with a Weight Basis of LoRAs
https://huggingface.co/papers/2602.15727]]>214ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-23--702177071. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
https://huggingface.co/papers/2602.13515
2. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
https://huggingface.co/papers/2602.16855
3. Unified Latents (UL): How to train your latents
https://huggingface.co/papers/2602.17270
4. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
https://huggingface.co/papers/2602.14457
5. Arcee Trinity Large Technical Report
https://huggingface.co/papers/2602.17004]]>https://api.spreaker.com/episode/70217707Sun, 22 Feb 2026 22:31:03 +0000ksterx【本日の論文】 1. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning https://huggingface.co/papers/2602.13515 2. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents...1. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
https://huggingface.co/papers/2602.13515
2. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
https://huggingface.co/papers/2602.16855
3. Unified Latents (UL): How to train your latents
https://huggingface.co/papers/2602.17270
4. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
https://huggingface.co/papers/2602.14457
5. Arcee Trinity Large Technical Report
https://huggingface.co/papers/2602.17004]]>240ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-22--702030361. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
https://huggingface.co/papers/2602.13515
2. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
https://huggingface.co/papers/2602.16855
3. Unified Latents (UL): How to train your latents
https://huggingface.co/papers/2602.17270
4. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
https://huggingface.co/papers/2602.14457
5. Arcee Trinity Large Technical Report
https://huggingface.co/papers/2602.17004]]>https://api.spreaker.com/episode/70203036Sat, 21 Feb 2026 22:30:45 +0000ksterx【本日の論文】 1. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning https://huggingface.co/papers/2602.13515 2. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents...1. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
https://huggingface.co/papers/2602.13515
2. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
https://huggingface.co/papers/2602.16855
3. Unified Latents (UL): How to train your latents
https://huggingface.co/papers/2602.17270
4. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
https://huggingface.co/papers/2602.14457
5. Arcee Trinity Large Technical Report
https://huggingface.co/papers/2602.17004]]>260ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-21--701829511. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
https://huggingface.co/papers/2602.13515
2. Unified Latents (UL): How to train your latents
https://huggingface.co/papers/2602.17270
3. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
https://huggingface.co/papers/2602.16855
4. "What Are You Doing?": Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing
https://huggingface.co/papers/2602.15569
5. Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents
https://huggingface.co/papers/2602.16699]]>https://api.spreaker.com/episode/70182951Fri, 20 Feb 2026 22:33:20 +0000ksterx【本日の論文】 1. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning https://huggingface.co/papers/2602.13515 2. Unified Latents (UL): How to train your latents...1. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
https://huggingface.co/papers/2602.13515
2. Unified Latents (UL): How to train your latents
https://huggingface.co/papers/2602.17270
3. Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
https://huggingface.co/papers/2602.16855
4. "What Are You Doing?": Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing
https://huggingface.co/papers/2602.15569
5. Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents
https://huggingface.co/papers/2602.16699]]>277ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-20--701609481. SLA2: Sparse-Linear Attention with Learnable Routing and QAT
https://huggingface.co/papers/2602.12675
2. RynnBrain: Open Embodied Foundation Models
https://huggingface.co/papers/2602.14979
3. Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation
https://huggingface.co/papers/2602.16705
4. CADEvolve: Creating Realistic CAD via Program Evolution
https://huggingface.co/papers/2602.16317
5. Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
https://huggingface.co/papers/2602.14080]]>https://api.spreaker.com/episode/70160948Thu, 19 Feb 2026 22:37:25 +0000ksterx【本日の論文】 1. SLA2: Sparse-Linear Attention with Learnable Routing and QAT https://huggingface.co/papers/2602.12675 2. RynnBrain: Open Embodied Foundation Models https://huggingface.co/papers/2602.14979 3. Learning Humanoid End-Effector Control for...1. SLA2: Sparse-Linear Attention with Learnable Routing and QAT
https://huggingface.co/papers/2602.12675
2. RynnBrain: Open Embodied Foundation Models
https://huggingface.co/papers/2602.14979
3. Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation
https://huggingface.co/papers/2602.16705
4. CADEvolve: Creating Realistic CAD via Program Evolution
https://huggingface.co/papers/2602.16317
5. Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
https://huggingface.co/papers/2602.14080]]>272ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-19--701389751. Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
https://huggingface.co/papers/2602.14111
2. SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
https://huggingface.co/papers/2602.12670
3. GLM-5: from Vibe Coding to Agentic Engineering
https://huggingface.co/papers/2602.15763
4. Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
https://huggingface.co/papers/2602.14299
5. ResearchGym: Evaluating Language Model Agents on Real-World AI Research
https://huggingface.co/papers/2602.15112]]>https://api.spreaker.com/episode/70138975Wed, 18 Feb 2026 22:41:05 +0000ksterx【本日の論文】 1. Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? https://huggingface.co/papers/2602.14111 2. SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks https://huggingface.co/papers/2602.12670 3....1. Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
https://huggingface.co/papers/2602.14111
2. SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
https://huggingface.co/papers/2602.12670
3. GLM-5: from Vibe Coding to Agentic Engineering
https://huggingface.co/papers/2602.15763
4. Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
https://huggingface.co/papers/2602.14299
5. ResearchGym: Evaluating Language Model Agents on Real-World AI Research
https://huggingface.co/papers/2602.15112]]>301ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-18--701180041. Experiential Reinforcement Learning
https://huggingface.co/papers/2602.13949
2. DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
https://huggingface.co/papers/2602.10809
3. REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
https://huggingface.co/papers/2602.14234
4. STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts
https://huggingface.co/papers/2602.14265
5. Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
https://huggingface.co/papers/2602.14492]]>https://api.spreaker.com/episode/70118004Tue, 17 Feb 2026 22:37:25 +0000ksterx【本日の論文】 1. Experiential Reinforcement Learning https://huggingface.co/papers/2602.13949 2. DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories https://huggingface.co/papers/2602.10809 3....1. Experiential Reinforcement Learning
https://huggingface.co/papers/2602.13949
2. DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
https://huggingface.co/papers/2602.10809
3. REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
https://huggingface.co/papers/2602.14234
4. STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts
https://huggingface.co/papers/2602.14265
5. Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
https://huggingface.co/papers/2602.14492]]>215ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-17--700894481. Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs
https://huggingface.co/papers/2602.10388
2. SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
https://huggingface.co/papers/2602.12783
3. MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
https://huggingface.co/papers/2602.12705
4. Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
https://huggingface.co/papers/2602.11858
5. OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
https://huggingface.co/papers/2602.08683]]>https://api.spreaker.com/episode/70089448Tue, 17 Feb 2026 00:51:40 +0000ksterx【本日の論文】 1. Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs https://huggingface.co/papers/2602.10388 2. SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise...1. Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs
https://huggingface.co/papers/2602.10388
2. SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
https://huggingface.co/papers/2602.12783
3. MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
https://huggingface.co/papers/2602.12705
4. Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
https://huggingface.co/papers/2602.11858
5. OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
https://huggingface.co/papers/2602.08683]]>221ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-05--697935071. CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
https://huggingface.co/papers/2602.01785
2. AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
https://huggingface.co/papers/2602.03786
3. No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs
https://huggingface.co/papers/2602.02103
4. MARS: Modular Agent with Reflective Search for Automated AI Research
https://huggingface.co/papers/2602.02660
5. daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
https://huggingface.co/papers/2602.02619]]>https://api.spreaker.com/episode/69793507Wed, 04 Feb 2026 22:35:27 +0000ksterx【本日の論文】 1. CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding https://huggingface.co/papers/2602.01785 2. AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration https://huggingface.co/papers/2602.03786 3....1. CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
https://huggingface.co/papers/2602.01785
2. AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
https://huggingface.co/papers/2602.03786
3. No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs
https://huggingface.co/papers/2602.02103
4. MARS: Modular Agent with Reflective Search for Automated AI Research
https://huggingface.co/papers/2602.02660
5. daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
https://huggingface.co/papers/2602.02619]]>236ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-04--697699341. Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
https://huggingface.co/papers/2602.00919
2. Kimi K2.5: Visual Agentic Intelligence
https://huggingface.co/papers/2602.02276
3. Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
https://huggingface.co/papers/2601.22060
4. Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
https://huggingface.co/papers/2602.02185
5. Closing the Loop: Universal Repository Representation with RPG-Encoder
https://huggingface.co/papers/2602.02084]]>https://api.spreaker.com/episode/69769934Tue, 03 Feb 2026 22:35:59 +0000ksterx【本日の論文】 1. Green-VLA: Staged Vision-Language-Action Model for Generalist Robots https://huggingface.co/papers/2602.00919 2. Kimi K2.5: Visual Agentic Intelligence https://huggingface.co/papers/2602.02276 3. Vision-DeepResearch: Incentivizing...1. Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
https://huggingface.co/papers/2602.00919
2. Kimi K2.5: Visual Agentic Intelligence
https://huggingface.co/papers/2602.02276
3. Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
https://huggingface.co/papers/2601.22060
4. Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
https://huggingface.co/papers/2602.02185
5. Closing the Loop: Universal Repository Representation with RPG-Encoder
https://huggingface.co/papers/2602.02084]]>203ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-02--697263641. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
https://huggingface.co/papers/2601.20833
2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
https://huggingface.co/papers/2601.20354
3. Scaling Embeddings Outperforms Scaling Experts in Language Models
https://huggingface.co/papers/2601.21204
4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
https://huggingface.co/papers/2601.22153
5. MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
https://huggingface.co/papers/2601.21821]]>https://api.spreaker.com/episode/69726364Sun, 01 Feb 2026 22:30:34 +0000ksterx【本日の論文】 1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives https://huggingface.co/papers/2601.20833 2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models...1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
https://huggingface.co/papers/2601.20833
2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
https://huggingface.co/papers/2601.20354
3. Scaling Embeddings Outperforms Scaling Experts in Language Models
https://huggingface.co/papers/2601.21204
4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
https://huggingface.co/papers/2601.22153
5. MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
https://huggingface.co/papers/2601.21821]]>282ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-02-01--697121671. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
https://huggingface.co/papers/2601.20833
2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
https://huggingface.co/papers/2601.20354
3. Scaling Embeddings Outperforms Scaling Experts in Language Models
https://huggingface.co/papers/2601.21204
4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
https://huggingface.co/papers/2601.22153
5. MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
https://huggingface.co/papers/2601.21821]]>https://api.spreaker.com/episode/69712167Sat, 31 Jan 2026 22:30:15 +0000ksterx【本日の論文】 1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives https://huggingface.co/papers/2601.20833 2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models...1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
https://huggingface.co/papers/2601.20833
2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
https://huggingface.co/papers/2601.20354
3. Scaling Embeddings Outperforms Scaling Experts in Language Models
https://huggingface.co/papers/2601.21204
4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
https://huggingface.co/papers/2601.22153
5. MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
https://huggingface.co/papers/2601.21821]]>294ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-31--696955451. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
https://huggingface.co/papers/2601.20833
2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
https://huggingface.co/papers/2601.20354
3. Scaling Embeddings Outperforms Scaling Experts in Language Models
https://huggingface.co/papers/2601.21204
4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
https://huggingface.co/papers/2601.22153
5. OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
https://huggingface.co/papers/2601.21639]]>https://api.spreaker.com/episode/69695545Fri, 30 Jan 2026 22:31:49 +0000ksterx【本日の論文】 1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives https://huggingface.co/papers/2601.20833 2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models...1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
https://huggingface.co/papers/2601.20833
2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
https://huggingface.co/papers/2601.20354
3. Scaling Embeddings Outperforms Scaling Experts in Language Models
https://huggingface.co/papers/2601.21204
4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
https://huggingface.co/papers/2601.22153
5. OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
https://huggingface.co/papers/2601.21639]]>179ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-30--696738951. Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
https://huggingface.co/papers/2601.20614
2. Advancing Open-source World Models
https://huggingface.co/papers/2601.20540
3. Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
https://huggingface.co/papers/2601.19325
4. DeepSeek-OCR 2: Visual Causal Flow
https://huggingface.co/papers/2601.20552
5. Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
https://huggingface.co/papers/2601.20209]]>https://api.spreaker.com/episode/69673895Thu, 29 Jan 2026 22:36:43 +0000ksterx【本日の論文】 1. Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation https://huggingface.co/papers/2601.20614 2. Advancing Open-source World Models...1. Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
https://huggingface.co/papers/2601.20614
2. Advancing Open-source World Models
https://huggingface.co/papers/2601.20540
3. Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
https://huggingface.co/papers/2601.19325
4. DeepSeek-OCR 2: Visual Causal Flow
https://huggingface.co/papers/2601.20552
5. Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
https://huggingface.co/papers/2601.20209]]>272ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-29--696540001. AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
https://huggingface.co/papers/2601.18491
2. AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
https://huggingface.co/papers/2601.18631
3. A Pragmatic VLA Foundation Model
https://huggingface.co/papers/2601.18692
4. Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models
https://huggingface.co/papers/2601.19834
5. AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
https://huggingface.co/papers/2601.17645]]>https://api.spreaker.com/episode/69654000Wed, 28 Jan 2026 22:34:24 +0000ksterx【本日の論文】 1. AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security https://huggingface.co/papers/2601.18491 2. AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning https://huggingface.co/papers/2601.18631 3....1. AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
https://huggingface.co/papers/2601.18491
2. AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
https://huggingface.co/papers/2601.18631
3. A Pragmatic VLA Foundation Model
https://huggingface.co/papers/2601.18692
4. Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models
https://huggingface.co/papers/2601.19834
5. AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
https://huggingface.co/papers/2601.17645]]>245ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-28--696303311. Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
https://huggingface.co/papers/2601.17058
2. daVinci-Dev: Agent-native Mid-training for Software Engineering
https://huggingface.co/papers/2601.18418
3. The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation
https://huggingface.co/papers/2601.17737
4. Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
https://huggingface.co/papers/2601.17027
5. Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
https://huggingface.co/papers/2601.17367]]>https://api.spreaker.com/episode/69630331Tue, 27 Jan 2026 22:29:04 +0000ksterx【本日の論文】 1. Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs https://huggingface.co/papers/2601.17058 2. daVinci-Dev: Agent-native Mid-training for Software Engineering https://huggingface.co/papers/2601.18418...1. Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
https://huggingface.co/papers/2601.17058
2. daVinci-Dev: Agent-native Mid-training for Software Engineering
https://huggingface.co/papers/2601.18418
3. The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation
https://huggingface.co/papers/2601.17737
4. Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
https://huggingface.co/papers/2601.17027
5. Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
https://huggingface.co/papers/2601.17367]]>264ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-27--696026661. LongCat-Flash-Thinking-2601 Technical Report
https://huggingface.co/papers/2601.16725
2. SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
https://huggingface.co/papers/2601.16746
3. TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
https://huggingface.co/papers/2601.14133
4. VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
https://huggingface.co/papers/2601.16973
5. Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory
https://huggingface.co/papers/2601.16296]]>https://api.spreaker.com/episode/69602666Mon, 26 Jan 2026 22:28:04 +0000ksterx【本日の論文】 1. LongCat-Flash-Thinking-2601 Technical Report https://huggingface.co/papers/2601.16725 2. SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents https://huggingface.co/papers/2601.16746 3. TwinBrainVLA: Unleashing the Potential of...1. LongCat-Flash-Thinking-2601 Technical Report
https://huggingface.co/papers/2601.16725
2. SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
https://huggingface.co/papers/2601.16746
3. TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
https://huggingface.co/papers/2601.14133
4. VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
https://huggingface.co/papers/2601.16973
5. Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory
https://huggingface.co/papers/2601.16296]]>204ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-26--695845791. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
https://huggingface.co/papers/2601.15876
2. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
https://huggingface.co/papers/2601.14724
3. LLM-in-Sandbox Elicits General Agentic Intelligence
https://huggingface.co/papers/2601.16206
4. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
https://huggingface.co/papers/2601.15165
5. BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
https://huggingface.co/papers/2601.15197]]>https://api.spreaker.com/episode/69584579Sun, 25 Jan 2026 22:27:25 +0000ksterx【本日の論文】 1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience https://huggingface.co/papers/2601.15876 2. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding...1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
https://huggingface.co/papers/2601.15876
2. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
https://huggingface.co/papers/2601.14724
3. LLM-in-Sandbox Elicits General Agentic Intelligence
https://huggingface.co/papers/2601.16206
4. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
https://huggingface.co/papers/2601.15165
5. BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
https://huggingface.co/papers/2601.15197]]>271ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-25--695748301. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
https://huggingface.co/papers/2601.15876
2. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
https://huggingface.co/papers/2601.14724
3. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
https://huggingface.co/papers/2601.15165
4. LLM-in-Sandbox Elicits General Agentic Intelligence
https://huggingface.co/papers/2601.16206
5. BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
https://huggingface.co/papers/2601.15197]]>https://api.spreaker.com/episode/69574830Sat, 24 Jan 2026 22:25:59 +0000ksterx【本日の論文】 1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience https://huggingface.co/papers/2601.15876 2. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding...1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
https://huggingface.co/papers/2601.15876
2. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
https://huggingface.co/papers/2601.14724
3. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
https://huggingface.co/papers/2601.15165
4. LLM-in-Sandbox Elicits General Agentic Intelligence
https://huggingface.co/papers/2601.16206
5. BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
https://huggingface.co/papers/2601.15197]]>222ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-24--695649881. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
https://huggingface.co/papers/2601.15876
2. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
https://huggingface.co/papers/2601.15165
3. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
https://huggingface.co/papers/2601.14724
4. BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
https://huggingface.co/papers/2601.15197
5. LLM-in-Sandbox Elicits General Agentic Intelligence
https://huggingface.co/papers/2601.16206]]>https://api.spreaker.com/episode/69564988Fri, 23 Jan 2026 22:25:13 +0000ksterx【本日の論文】 1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience https://huggingface.co/papers/2601.15876 2. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models...1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
https://huggingface.co/papers/2601.15876
2. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
https://huggingface.co/papers/2601.15165
3. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
https://huggingface.co/papers/2601.14724
4. BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
https://huggingface.co/papers/2601.15197
5. LLM-in-Sandbox Elicits General Agentic Intelligence
https://huggingface.co/papers/2601.16206]]>260ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-23--695516071. Agentic Reasoning for Large Language Models
https://huggingface.co/papers/2601.12538
2. MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
https://huggingface.co/papers/2601.12346
3. Rethinking Video Generation Model for the Embodied World
https://huggingface.co/papers/2601.15282
4. Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance
https://huggingface.co/papers/2601.14171
5. Behavior Knowledge Merge in Reinforced Agentic Models
https://huggingface.co/papers/2601.13572]]>https://api.spreaker.com/episode/69551607Thu, 22 Jan 2026 22:29:50 +0000ksterx【本日の論文】 1. Agentic Reasoning for Large Language Models https://huggingface.co/papers/2601.12538 2. MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents https://huggingface.co/papers/2601.12346 3. Rethinking Video Generation...1. Agentic Reasoning for Large Language Models
https://huggingface.co/papers/2601.12538
2. MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
https://huggingface.co/papers/2601.12346
3. Rethinking Video Generation Model for the Embodied World
https://huggingface.co/papers/2601.15282
4. Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance
https://huggingface.co/papers/2601.14171
5. Behavior Knowledge Merge in Reinforced Agentic Models
https://huggingface.co/papers/2601.13572]]>187ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-22--695389681. Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
https://huggingface.co/papers/2601.12993
2. Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
https://huggingface.co/papers/2601.11655
3. Toward Efficient Agents: Memory, Tool learning, and Planning
https://huggingface.co/papers/2601.14192
4. OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer
https://huggingface.co/papers/2601.14250
5. FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
https://huggingface.co/papers/2601.13836]]>https://api.spreaker.com/episode/69538968Wed, 21 Jan 2026 22:31:23 +0000ksterx【本日の論文】 1. Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization https://huggingface.co/papers/2601.12993 2. Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey...1. Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
https://huggingface.co/papers/2601.12993
2. Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
https://huggingface.co/papers/2601.11655
3. Toward Efficient Agents: Memory, Tool learning, and Planning
https://huggingface.co/papers/2601.14192
4. OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer
https://huggingface.co/papers/2601.14250
5. FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
https://huggingface.co/papers/2601.13836]]>188ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-21--695249541. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
https://huggingface.co/papers/2601.11077
2. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
https://huggingface.co/papers/2601.08808
3. Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation
https://huggingface.co/papers/2601.10880
4. NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
https://huggingface.co/papers/2601.11004
5. Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
https://huggingface.co/papers/2601.11061]]>https://api.spreaker.com/episode/69524954Tue, 20 Jan 2026 22:31:14 +0000ksterx【本日の論文】 1. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development https://huggingface.co/papers/2601.11077 2. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge https://huggingface.co/papers/2601.08808 3. Medical...1. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
https://huggingface.co/papers/2601.11077
2. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
https://huggingface.co/papers/2601.08808
3. Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation
https://huggingface.co/papers/2601.10880
4. NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
https://huggingface.co/papers/2601.11004
5. Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
https://huggingface.co/papers/2601.11061]]>267ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-20--69511506https://api.spreaker.com/episode/69511506Mon, 19 Jan 2026 22:28:10 +0000ksterx255ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-19--69500887https://api.spreaker.com/episode/69500887Mon, 19 Jan 2026 00:56:21 +0000ksterx223ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-17--69473897https://api.spreaker.com/episode/69473897Fri, 16 Jan 2026 22:27:31 +0000ksterx288ai,huggingface,papersfalsefullhttps://www.spreaker.com/episode/daily-ai-papers-briefing-2026-01-16--69461181・1. Controlled Self-Evolution for Algorithmic Code Optimization
・2. DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
・3. MAXS: Meta-Adaptive Exploration with LLM Agents
・4. A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation
・5. Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

【参考リンク】
Controlled Self-Evolution for Algorithmic Code Optimization: https://huggingface.co/papers/2601.07348
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation: https://huggingface.co/papers/2601.09688
MAXS: Meta-Adaptive Exploration with LLM Agents: https://huggingface.co/papers/2601.09259
A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation: https://huggingface.co/papers/2601.09274
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning: https://huggingface.co/papers/2601.09088]]>https://api.spreaker.com/episode/69461181Thu, 15 Jan 2026 23:40:09 +0000ksterx【本日の論文】 ・1. Controlled Self-Evolution for Algorithmic Code Optimization ・2. DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation ・3. MAXS: Meta-Adaptive Exploration with LLM Agents ・4. A^3-Bench:...・1. Controlled Self-Evolution for Algorithmic Code Optimization
・2. DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
・3. MAXS: Meta-Adaptive Exploration with LLM Agents
・4. A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation
・5. Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

【参考リンク】
Controlled Self-Evolution for Algorithmic Code Optimization: https://huggingface.co/papers/2601.07348
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation: https://huggingface.co/papers/2601.09688
MAXS: Meta-Adaptive Exploration with LLM Agents: https://huggingface.co/papers/2601.09259
A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation: https://huggingface.co/papers/2601.09274
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning: https://huggingface.co/papers/2601.09088]]>237ai,huggingface,papersfalsefull