ずんだもんのHugging Faceニュース

【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? 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

【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? 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

【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
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

【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 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

【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. 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

【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 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

【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: 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

【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: 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

【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. 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

【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
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

【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
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

【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. 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

【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
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

【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, 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

【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 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

【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 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

【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
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

【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 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

【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
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

【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
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

【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
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

【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?
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

【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?
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

【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?
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

【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 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

【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
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

【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
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

【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. 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

【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 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

【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 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

【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 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

【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
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

【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 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

【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
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

【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 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

【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
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

【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
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

【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?
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

【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 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

【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
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