Daily Papers of 2026-11-05

  1. FrontierPhysics: Evaluating Agents for End-to-End Physics Research 61 upvotes, #1 of 2026-11-05
  2. From Pixels to Actions - Towards Native Vision-Language-Action Policies 60 upvotes, #2 of 2026-11-05
  3. Halley: A Predictive Control Plane for Optical AI Data Center Networks 39 upvotes, #3 of 2026-11-05
  4. What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? 38 upvotes, #4 of 2026-11-05
  5. GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling 37 upvotes, #5 of 2026-11-05
  6. VideoMemBench: How Well Do MLLMs Remember in Video Conversations? 34 upvotes, #6 of 2026-11-05
  7. Turns Matter: Advancing Streaming Video RL via Turn-Level Credit 30 upvotes, #7 of 2026-11-05
  8. PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data 27 upvotes, #8 of 2026-11-05
  9. On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation 23 upvotes, #9 of 2026-11-05
  10. EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL 23 upvotes, #9 of 2026-11-05
  11. MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation 22 upvotes, #11 of 2026-11-05
  12. Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents 19 upvotes, #12 of 2026-11-05
  13. D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding 19 upvotes, #12 of 2026-11-05
  14. TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens 17 upvotes, #14 of 2026-11-05
  15. Solv3R: 3D Looped Transformer as a Multi-view Solver 17 upvotes, #14 of 2026-11-05
  16. Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost 16 upvotes, #16 of 2026-11-05
  17. Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs 15 upvotes, #17 of 2026-11-05
  18. SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding 14 upvotes, #18 of 2026-11-05
  19. PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World 11 upvotes, #19 of 2026-11-05
  20. The SIMPLE Law for Energy Cost of LLM Inference 10 upvotes, #20 of 2026-11-05
  21. VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation 10 upvotes, #20 of 2026-11-05
  22. AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds 9 upvotes, #22 of 2026-11-05
  23. LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers 9 upvotes, #22 of 2026-11-05
  24. NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers 9 upvotes, #22 of 2026-11-05
  25. VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing 8 upvotes, #25 of 2026-11-05
  26. LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds 8 upvotes, #25 of 2026-11-05
  27. How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates 7 upvotes, #27 of 2026-11-05
  28. Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention 6 upvotes, #28 of 2026-11-05
  29. SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding? 6 upvotes, #28 of 2026-11-05
  30. VeriSpoof: Beyond Real or Fake with One Audio LLM 5 upvotes, #30 of 2026-11-05
  31. Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors 4 upvotes, #31 of 2026-11-05
  32. Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization 4 upvotes, #31 of 2026-11-05
  33. Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting 4 upvotes, #31 of 2026-11-05
  34. GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats 3 upvotes, #34 of 2026-11-05
  35. TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation 2 upvotes, #35 of 2026-11-05
  36. UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling 2 upvotes, #35 of 2026-11-05
  37. HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias 1 upvotes, #37 of 2026-11-05
  38. DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI 0 upvotes, #38 of 2026-11-05

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.