Daily Papers of 2026-11-10

  1. Learning Heterogeneous Tactile Representation for General Dexterous Manipulation 102 upvotes, #1 of 2026-11-10
  2. WorldFoundry: Towards Unified Infrastructure for World Intelligence 58 upvotes, #2 of 2026-11-10
  3. Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery 56 upvotes, #3 of 2026-11-10
  4. Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning 40 upvotes, #4 of 2026-11-10
  5. Flide: Accelerating Decision Inference with Exact State Forking 35 upvotes, #5 of 2026-11-10
  6. Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization 35 upvotes, #5 of 2026-11-10
  7. ReproBridge: Building Reproducibility into ML Research Artifacts 32 upvotes, #7 of 2026-11-10
  8. InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure 32 upvotes, #7 of 2026-11-10
  9. Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages 22 upvotes, #9 of 2026-11-10
  10. SWAM: Scaling World Action Models with Cross-Modal Alignment 22 upvotes, #9 of 2026-11-10
  11. How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time 15 upvotes, #11 of 2026-11-10
  12. How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate? 13 upvotes, #12 of 2026-11-10
  13. SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research 12 upvotes, #13 of 2026-11-10
  14. MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification 12 upvotes, #13 of 2026-11-10
  15. e-means: outperforming k-means (in one-tenth the epochs) 11 upvotes, #15 of 2026-11-10
  16. FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning 10 upvotes, #16 of 2026-11-10
  17. TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation 9 upvotes, #17 of 2026-11-10
  18. AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations 8 upvotes, #18 of 2026-11-10
  19. Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation 8 upvotes, #18 of 2026-11-10
  20. All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States 6 upvotes, #20 of 2026-11-10
  21. LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation 5 upvotes, #21 of 2026-11-10
  22. Training Vision Transformers to Focus: Emergence of Spatial Attention Head Specialization 5 upvotes, #21 of 2026-11-10
  23. FlyHash for LLM Agent Memory: An Empirical Validation and a New Application 4 upvotes, #23 of 2026-11-10
  24. SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AI 4 upvotes, #23 of 2026-11-10
  25. JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation 4 upvotes, #23 of 2026-11-10
  26. FraudBench: A Legal Evaluation of AI Deception 4 upvotes, #23 of 2026-11-10
  27. RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill 3 upvotes, #27 of 2026-11-10
  28. onóna: Twin Embeddings with Tied Unembeddings 3 upvotes, #27 of 2026-11-10
  29. Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models 2 upvotes, #29 of 2026-11-10
  30. PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals 2 upvotes, #29 of 2026-11-10
  31. InstantHMR : Real-Time Human Mesh Recovery on Your Phone 2 upvotes, #29 of 2026-11-10
  32. Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition 2 upvotes, #29 of 2026-11-10
  33. Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics Engines 2 upvotes, #29 of 2026-11-10
  34. Creative Priming: Decoupling Process from Product to Escape the Creative Paradox 2 upvotes, #29 of 2026-11-10
  35. EmoHarness: Boosting Multimodal Emotion Understanding with Meta-Harness Evolving 2 upvotes, #29 of 2026-11-10
  36. Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks 2 upvotes, #29 of 2026-11-10
  37. Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching 1 upvotes, #37 of 2026-11-10
  38. Energy-Tweedie: Score meets Score, Energy meets Energy 1 upvotes, #37 of 2026-11-10
  39. Horizon-Scalable Q-Learning 1 upvotes, #37 of 2026-11-10

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.