Trendoday
Hugging FaceArchive · weekly

HF Daily Papers: week 44, 2026

During week 44 of 2026 (Oct 26 – Nov 1), 200 different entries appeared on HF Daily Papers across 7 days of checks (84 checks in total). “A-RSI: Adaptive Task Refresh for Zero-Data Multimodal…” ranked highest overall: on the list on 3 of 7 days, best #2, average #2.6. 0 entries stayed on the list every day. 10 of the top 10 were not in the previous week's top 10. 167 entries made their first appearance, led by “A-RSI: Adaptive Task Refresh for Zero-Data Multimodal…”.

  1. 1
    3/7days
  2. 2
    3/7days
  3. 3
    3/7days
  4. 4
    4/7days
  5. 5
    3/7days
  6. 6
    Intrinsic Distribution Matching↗
    best #1 · avg #6.2new
    3/7days
  7. 7
    3/7days
  8. 8
    3/7days
  9. 9
    3/7days
  10. 10
    3/7days
  11. 11
    3/7days
  12. 12
    3/7days
  13. 13
    3/7days
  14. 14
    3/7days
  15. 15
    3/7days
  16. 16
    3/7days
  17. 17
    3/7days
  18. 18
    4/7days
  19. 19
    3/7days
  20. 20
    3/7days
  21. 21
    3/7days
  22. 22
    3/7days
  23. 23
    3/7days
  24. 24
    3/7days
  25. 25
    3/7days
  26. 26
    2/7days
  27. 27
    3/7days
  28. 28
    3/7days
  29. 29
    2/7days
  30. 30
    3/7days
  31. 31
    Multi-Token Prediction Done Right↗
    best #15 · avg #19.3new
    3/7days
  32. 32
    OvisOCR3 Technical Report↗
    best #6 · avg #13.2new
    3/7days
  33. 33
    3/7days
  34. 34
    3/7days
  35. 35
    3/7days
  36. 36
    2/7days
  37. 37
    3/7days
  38. 38
    2/7days
  39. 39
    3/7days
  40. 40
    3/7days
  41. 41
    3/7days
  42. 42
    2/7days
  43. 43
    2/7days
  44. 44
    2/7days
  45. 45
    3/7days
  46. 46
    3/7days
  47. 47
    4/7days
  48. 48
    3/7days
  49. 49
    2/7days
  50. 50
    2/7days

Also on the list this week (150)

Online Dense Reinforcement Learning with Planning-Grounding Agent… · Omni-InteractScope: Benchmarking Proactive and Agentic Interaction… · RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on… · Beyond the Estimate: Wiener-Informed Decoding for Easier Training of… · The Lexical Imprint of Pre-training Data · UserArena: Benchmarking Interactive User Simulation for Long-Horizon… · Reading, Writing, Sharing, and Interacting with the World through… · StreamVibe: Proactive Video Agents for Evolving User Intent · Different Tasks, Different Timesteps: Temporal Task-Aware… · TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving · DynaFlow: Learning Free-Form Multi-Agent Orchestration · RSIHub: A Composable Framework for Agent-Evolution Methods · EvalResearchBench: Can AI Agents Build Their Own Feedback for… · Trajectory2Gym: Decision-Grounded Compositional Interaction… · HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World… · Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems · Rollback: Experience Backtracking in World Models for Policy… · Spatial Audio Generation and Editing with Executable Plans and… · Eat Your Precision: Precision Objective Mitigates Reward Hacking in… · RynnUnify: Towards Unified Embodied Brain · LociArt: A Unified Paradigm for Free-Style Local Video Stylization · InteractiveWorld: A Verifiable Human-Centric Environment for… · Work Agents: Systems, Capabilities, and Optimization · Omni-Woodpecker: Hallucination Correction via Evidence-Prior… · What Effort Level Should I Choose? On the Economics of Reasoning… · Δτ-Bench: Pushing Agents Toward a Moving Capability · On the SPOT: Enhancing Speculative Decoding for Diffusion Language… · RSI Arena: Towards Recursive Self-Improvement with Human Feedback · Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt… · Your Policy Is Secretly a Harness: The Decision Geometry of Agent… · Dual Exam: Controlled Evaluation of Multimodal Agents and World Models · Trustworthy Recursive Self-Improvement in the Era of Large Models:… · FilmFlow: Agentic System for 3D Virtual Film Cinematography · Every Weight Is a Path of Shared Discrete Decisions · IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems · Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and… · TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language… · LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data · Training Foundation Models with a Single Algorithm · WorldCast: World-Consistent Character Video Generation with… · WeVisOne-VL: Unified Visual Perception from Objects to Pixels · Continual Learning Exam: Benchmarking Long-Horizon RSI and… · HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction · World-in-Context: Interactive Video World Modeling with In-Context… · S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM… · DTCA: Denoising Token Credit Assignment for Reinforcement Learning… · AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos · Principia: Test-Time Hypotheses to Principle Construction for… · Representation Redistribution in Sparse Autoencoders · Diffusion Language Models Change Speed Across Tasks and Languages · What Generation Knows: Unlocking Fine-Grained Understanding in… · ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn… · The LLM-Attacker: A Unified Red-Team Framework for Privacy… · Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation · Cross-modal Steering Vectors Exist Across Both Image and Text… · Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful… · Evolving to Match Capabilities: Improving Harness Self-Evolution via… · Build, Don't Play: Self-Improving LLM Research Agents Develop a… · DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations… · On-Policy Self-Training: Data-Free Self-Improvement in Large… · RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with… · RIDAR: Safeguarding Research Integrity in Autonomous Research Agents… · BrickWright: Agentic Creation of Physically Feasible Brick Builds · miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4… · Rethinking Video Storage for AI Training: Breaking Cross-Frame… · Function-Space Temporal Self-Distillation for Policy Optimization · RTAformer: Relation-Transition-Aware Transformer for Video Scene… · EmbodiedLab: Benchmarking Embodied Agents That Act to Know · Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent… · DirCast: Live Esports Directing and Commentary with a Single… · DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse… · ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple… · How Far Can Coding Agents Go in Visual Generation? · Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon… · RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian… · ReGE: Stronger Agents through Experience Synthesis · Timestral · HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per… · IF-MAP: Influence-Function-Inspired Agent Prioritization in… · Building Auditable AI Text Detectors with Sparse Autoencoders · FLOMSS: Generative Music Source Separation by Flow Matching · PaperFormalizer: Author-in-the-Loop Autoformalization of Research… · TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon… · MMVistaReason: Toward Open-Data and Post-Training Recipes for… · More Memory, Better Videos? A Controlled Study of Visual Memory in… · Bridging Exploration and Persona: Information-Directed Dueling for… · Editing Images into Reusable Layers via Compositional Edit-Prior… · Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty… · iPrefBench: A User-Centric Benchmark for Personalized Mobile Use… · Toward Recursive Self-Improvement in Physical AI · CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful… · DuoLM: Fast and Effective Personalized Recommendation with Language… · AgentProofBench: Benchmarking Reusable Verifiers for Web Agents · MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent… · Self-Distilling Future Video Representations for World Action Models · What Makes a Good Unmasking Policy? A Controlled Study of Learned… · RouteWeaver: Weaving Mode Selection and Execution into Unified LLM… · CausalAlign: Causal Alignment of Video Generation Models for… · How Much Does the Hint Matter? Scope Conditions for Hindsight… · Heartbeat Thinking: Speculative Reasoning and Tool Execution While… · Who Takes the Lead? Model Ability and Task-Conditioned Collaboration… · Speculative Diffusion is a Tale of Two Tradeoffs · Deep Fusion Memory: A Chunk-Level Parametric Memory for Large… · Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM… · Rethinking Verification in Agent Harnesses · AnyGameRenderer: Entity-Consistent Generative Rendering Across Games… · JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making · Verus-Insight: Towards Explainable Artifact Detection in… · RoboJev: An Open Vision-Language Judge for Robot Success Detection · SearchHorizonBench: A Benchmark for Search Value in AI Agents · MambaAct: Efficient Mamba Action Experts for Flow-Matching… · MolLean: A Process-Verifiable Language for Chemical Reasoning · Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous… · Deep Search in Real-World Web Environments · Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D… · Vision-Language-Action or World-Action? Just Action Models · RoboJudge: Multimodal Language Models as Judges for Embodied Video… · Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions · AgentVQA: A Unified Benchmark for Agentic Visual Understanding · F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D… · Nested Sparsity for Scalable Pretraining and Continual Learning · Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than… · Rethinking Sequence Compression with Test-time Regression · DialFork: Going Beyond Factuality to Evaluate Procedural… · OBB-PBD: Extending Parallel Box Decoding to Oriented Bounding Boxes… · Making MLLM Latents Matter: Factor-Aware Predictive Learning for… · Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning… · Semantic Concept Steering Breaks the Explanation Drift Loop in… · Policy-Mask: Budget-Aware Adaptation of Diffusion Features to… · Intrinsic Goals for Autonomous Agents: Hierarchical Exploration… · SplatLab: Autonomous Scientific Discovery for 3DGS Research · Can LLMs Uncover Hidden Physical Laws through Free Exploration? · LaLa-World: Scaling Latent World Models with Natural Language Actions · Code2Video-Compass: A Comprehensive Benchmark for General-Purpose… · Meta Expert: Cross-Layer Expert Sharing for Storage- and… · Beyond Watching and Searching: Benchmarking Agents for… · Your LR Schedule May Not Be Principled: Effective Learning Rate… · DISC: Domain-Integrated Similarity Cost for Time-Series Dataset · TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation… · Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact… · KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks · Mycelium: A Meta-Study of Hallucination Detection Across Provenance,… · Trust Mechanisms for Offline Generative AI at the Edge: A… · LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification · Ψ-0.6: Adaptive Streams of Thought in a Unified Vision-Language… · MLE-World: Predicting Machine Learning Experiment Outcomes with a… · Joint or Per-Option? Compact Encoders for Closed-Set Decisions from… · Does LeWorldModel Preserve Local Action Geometry? · EnvLunch: The Environment as a Free Lunch for Learning to Interact · Learning and Reasoning with Geometry: How Generation Helps Spatial…

Ordered by Trendoday score: position on each day's list, weighted by how often it was there, summed over the period. Ranks are UTC days. All HF Daily Papers archives

Daily lists

Oct 26Oct 27Oct 28Oct 29Oct 30Oct 31Nov 1