Trendoday
Hugging FaceArchive · weekly

HF Daily Papers: week 45, 2026

During week 45 of 2026 (Nov 2 – Nov 8), 189 different entries appeared on HF Daily Papers across 7 days of checks (81 checks in total). “Halley: A Predictive Control Plane for Optical AI Data…” ranked highest overall: on the list on 4 of 7 days, best #5, average #8.2. 0 entries stayed on the list every day. 10 of the top 10 were not in the previous week's top 10. 158 entries made their first appearance, led by “Halley: A Predictive Control Plane for Optical AI Data…”. This week is still in progress; the list updates until it closes.

  1. 1
    4/7days
  2. 2
    3/7days
  3. 3
    3/7days
  4. 4
    3/7days
  5. 5
    3/7days
  6. 6
    4/7days
  7. 7
    3/7days
  8. 8
    3/7days
  9. 9
    4/7days
  10. 10
    3/7days
  11. 11
    4/7days
  12. 12
    3/7days
  13. 13
    3/7days
  14. 14
    3/7days
  15. 15
    3/7days
  16. 16
    4/7days
  17. 17
    3/7days
  18. 18
    3/7days
  19. 19
    3/7days
  20. 20
    3/7days
  21. 21
    4/7days
  22. 22
    2/7days
  23. 23
    2/7days
  24. 24
    2/7days
  25. 25
    3/7days
  26. 26
    3/7days
  27. 27
    3/7days
  28. 28
    3/7days
  29. 29
    3/7days
  30. 30
    2/7days
  31. 31
    2/7days
  32. 32
    3/7days
  33. 33
    2/7days
  34. 34
    2/7days
  35. 35
    2/7days
  36. 36
    3/7days
  37. 37
    2/7days
  38. 38
    3/7days
  39. 39
    2/7days
  40. 40
    2/7days
  41. 41
    2/7days
  42. 42
    2/7days
  43. 43
    2/7days
  44. 44
    2/7days
  45. 45
    2/7days
  46. 46
    2/7days
  47. 47
    3/7days
  48. 48
    2/7days
  49. 49
    2/7days
  50. 50
    2/7days

Also on the list this week (139)

IdeaTaste: Do LLMs Share the Research Taste of Human Researchers? · Wave Forcing: Towards Speed-of-Light Streaming Video Generation · MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for… · Behind Video Generation: Observations and Insights on Multimodal… · Axion 1.0: Open Agent Foundation Models, Simplified · Latent Reasoning in Continuous Space for Unified Multimodal Models · Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and… · ToolSpace: Scaling Tool-Centric Environment Synthesis for… · REA: A Routed Embodied Agent Runtime for Asynchronous… · Wizard: Manipulate Any World in Real Time via Agentic Control · Democratizing Robot-Use Agents: A Unified Harness with Open Models · Solv3R: 3D Looped Transformer as a Multi-view Solver · Advances in Agentic Computer Graphics · SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and… · VideoMemBench: How Well Do MLLMs Remember in Video Conversations? · CUA-Master: Scaling Computer-use Agents through Open-World Recursive… · Order-Only On-Policy Distillation · YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn… · VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing · HiFOR: Hierarchical Foresight with Action-Guided World Grounding for… · No Channels Left Behind: Understanding Diffusion Acceleration… · OSWAM: An Effective World Action Model with One-Step Action Generation · NorthCUA Technical Report: Turbocharging Computer-Use Agents through… · Human-to-Robot Transfer via Bridging Representation and Action Space… · MoviEdit: Long-form Multi-Shot Video Editing Made Easy · Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader… · CEPO: A General Framework for Improving Prompt Optimization in… · CoworkOS:Scaling Agent Coworkers for Real-world Automation · WebHarbor: Docking Real Websites for Evolving GUI Agent Environments · ReLift: Dense 3D Tracking as Lifted Trajectory Repair · VA-TDM: A Unified View for Improving Few-Step Diffusion Models by… · From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal… · CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents · Adversarial Speculative Reasoning Improves Long Horizon Agents · SpecOPD: Branch-Parallel On-Policy Distillation for Speculative… · SWE-Trail: History-Guided Trajectory Collection for Coding Agent… · Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities · Reviso: Not All Visual Evidence Deserves Equal Attention in Video… · Lost in Recovery: Demystifying Recovery Behavior of Computer-Use… · LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers · Dory1.0-4B: A Looped Normalized-GPT · Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot… · AnchorComplete: Recovering Complete Scene Meshes from Partial Point… · FlowTranslator: Training-Free In-Image Machine Translation with… · On the Generalization Limitation of On-Policy Distillation for… · RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild · PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing… · SpecPilot: Autonomous Algorithm Discovery and Systems Optimization… · MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery · "Shall We Approve?" Consequence-Aware Approval for Autonomous Coding… · CrossSWE: Benchmarking Cross-Repository Joint Development for Coding… · Probing Spatial State Representations in Visual Foundation Models · ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for… · How I Aligned Your Model: Scaling Up Multilingual Safety Training… · When Does Latent Prediction Error Support Physical Surprise Claims… · L3G-World: Real-Time Infinite World Generation with Latent 3D… · Training Foundation Models with a Single Algorithm · WeFair: Fidelity-Aware Alignment from Human Feedback for… · Avatar Intelligence: Amplifying Human Agency Through Persistent… · Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space… · Multi-Token Prediction Done Right · Learning Quality-Controllable Robot Policies with Iterative… · FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe… · WorldBridge: Bridging Video and Action for Task Generalization in… · Recursa: Toward Recursively Self-Improving Foundation Model Systems · Can AI Reviewers See Your Efforts to Improve Your Paper? A… · GLOW-FM: Efficient Generative Low-Light Image Enhancement with… · Switch-SWE: Do Coding Agents Hold Focus When Switching Between… · Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use… · PrimeSim: A Generalist World Model Simulator from Large-Scale… · When Requirements Interact: Scaling Long-Horizon Coding via… · DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained… · DecisionRank: On-Policy Distillation for Decision-Model Rerankers · You don't need long context · LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive… · History Forcing: Distilling History-Dependent Continuations for… · Near-Zero Token Embeddings Silently Stall Training in Gated Sequence… · A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement · PhysInsert: Physically Plausible Object Insertion with Geometric… · Measuring AI Agents as Teammates with Collaborative Intelligence · BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion… · Look Only When Needed: Certificate-Guided Visual Routing for… · LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents · WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale… · On the Origin and Evolution of Training-Inference Mismatch in LLM… · Scaling Lean Theorem Proving for Real-World Code Verification · Investor's Last Exam: Can AI Agents Do Equity Investment Without… · OpenFlyV2: An onboard vision-language-action model for aerial… · SOMA: A Benchmark for Fine-Grained Egocentric Behavior and… · LOLPlay: Benchmarking Real-Time Visual Agents in League of Legends · Glance: The Generator Is Its Own Reranker · SleuthVLM: Do We Really Need Audio-in-Video for Omni Video… · HALO: Human-Grounded Granular Evaluation of Proactive Agents · A Broader Look into MLLM's Retrieval Heads · Cross-Primitive Consistency in Jev · HairDeck: Animation-Ready Stylized Hair Cards from a Single Image · Online Dense Reinforcement Learning with Planning-Grounding Agent… · Reducing Representational Interference in Retrieval Embeddings with… · Your Benchmark Is an Empirical Measure Over Difficulty · RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human… · MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with… · MemSteer: Turning User Histories into Supervision for Agent Memory… · Co-Design Bench: Multimodal Collaborative Coding Evaluation for… · Intrinsic Distribution Matching · CoSTA: Compressed Speech Token Adaptation for Efficient Spoken… · GEPA-Curator: Curated Learning for Self Improving Agents · Multi-Agent Relay Thinking · Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public… · WeVisCut: The Whole Editing Room in One Agent From Narration to… · AB-Attention: Accurate Block Attention for Accelerating Video… · IntReal: A Real-World Dataset and Benchmark for Multimodal… · AskStream: When and What to Ask Proactively under Uncertainty in… · EditAgent: Rethinking Agentic Image Editing · Library of Layers (LoL): Adaptively Ordering Transformer Layers at… · WorkFactory: Turning Professional Intents into Executable Work for… · Supervising the Visible State: Separating Representation from View… · SO-101 Bench: Accessible Spatial Manipulation · VeriSpoof: Beyond Real or Fake with One Audio LLM · VibeGame: Prompt-to-Game Development with AI-Native Engine and… · OpenFrontiers: A Collection of Open Research Problems and a… · Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek… · PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse… · WebAnything: From the Wild Web to Scalable Agent Environments · Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical… · DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context… · Matched Capabilities, Different Behaviors: A Controlled Study of MCP… · Your LR Schedule May Not Be Principled: Effective Learning Rate… · VoxLock: Target-Speaker Extraction for Voice Agents Without an… · RoboArchitect: Automating the Design of Robotic Agents with… · RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration… · TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of… · DR Pixel: Page-Native Deep Research with Vision-Language Models · Self-Improvement with Auxiliary Rewards: Learning from Verified… · Can Large Language Model Agents Learn by Watching Tutorial Videos? · Amortizing Sequential Experimental Design in Reasoning LLMs · Think Twice: The Metis-1.6 Technical Report · SIMIT: Self-Improving Vision-Language Models via Imagination at… · Is Your Long-Horizon Benchmark Really Deep? Measuring and… · GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian…

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

Nov 2Nov 3Nov 4Nov 5Nov 6Nov 7Nov 8