Daily Papers of 2026-10-26

  1. Function-Space Temporal Self-Distillation for Policy Optimization 140 upvotes, #1 of 2026-10-26
  2. UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents 63 upvotes, #2 of 2026-10-26
  3. HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games 57 upvotes, #3 of 2026-10-26
  4. RynnUnify: Towards Unified Embodied Brain 55 upvotes, #4 of 2026-10-26
  5. RSIHub: A Composable Framework for Agent-Evolution Methods 49 upvotes, #5 of 2026-10-26
  6. Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs 40 upvotes, #6 of 2026-10-26
  7. On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models 39 upvotes, #7 of 2026-10-26
  8. Dual Exam: Controlled Evaluation of Multimodal Agents and World Models 36 upvotes, #8 of 2026-10-26
  9. DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model 32 upvotes, #9 of 2026-10-26
  10. DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning 28 upvotes, #10 of 2026-10-26
  11. Speculative Diffusion is a Tale of Two Tradeoffs 25 upvotes, #11 of 2026-10-26
  12. Every Weight Is a Path of Shared Discrete Decisions 25 upvotes, #11 of 2026-10-26
  13. TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics 20 upvotes, #13 of 2026-10-26
  14. DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation 20 upvotes, #13 of 2026-10-26
  15. MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning 16 upvotes, #15 of 2026-10-26
  16. SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing 16 upvotes, #15 of 2026-10-26
  17. Building Auditable AI Text Detectors with Sparse Autoencoders 16 upvotes, #15 of 2026-10-26
  18. FLOMSS: Generative Music Source Separation by Flow Matching 15 upvotes, #18 of 2026-10-26
  19. Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models 15 upvotes, #18 of 2026-10-26
  20. DuoLM: Fast and Effective Personalized Recommendation with Language Models 13 upvotes, #20 of 2026-10-26
  21. Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows 12 upvotes, #21 of 2026-10-26
  22. MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation 12 upvotes, #21 of 2026-10-26
  23. Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding 12 upvotes, #21 of 2026-10-26
  24. LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification 12 upvotes, #21 of 2026-10-26
  25. FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models 12 upvotes, #21 of 2026-10-26
  26. JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making 11 upvotes, #26 of 2026-10-26
  27. Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction 11 upvotes, #26 of 2026-10-26
  28. Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval 9 upvotes, #28 of 2026-10-26
  29. PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean 9 upvotes, #28 of 2026-10-26
  30. HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training 9 upvotes, #28 of 2026-10-26
  31. The fixed-point bundle method over product-of-simplex domains arising from game equilibria 8 upvotes, #31 of 2026-10-26
  32. RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation 7 upvotes, #32 of 2026-10-26
  33. DISC: Domain-Integrated Similarity Cost for Time-Series Dataset 7 upvotes, #32 of 2026-10-26
  34. Does LeWorldModel Preserve Local Action Geometry? 7 upvotes, #32 of 2026-10-26
  35. KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks 6 upvotes, #35 of 2026-10-26
  36. What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories 6 upvotes, #35 of 2026-10-26
  37. LoCA: Enabling Multi-Modality in Geospatial Location Encoders 6 upvotes, #35 of 2026-10-26
  38. A path-following framework on fiber bundle for variational inequalities 5 upvotes, #38 of 2026-10-26
  39. How Much Feedback Is Needed to Break Template Protection? The Geometric Vulnerability of Biometric Authentication 5 upvotes, #38 of 2026-10-26
  40. Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection 4 upvotes, #40 of 2026-10-26
  41. Judging the Justification: Decision Certificate Supervision for Generative Reward Models 4 upvotes, #40 of 2026-10-26
  42. WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot 3 upvotes, #42 of 2026-10-26
  43. On the Token Collapse Phenomenon in Textual Graph Soft Prompting 3 upvotes, #42 of 2026-10-26
  44. FLORA: An Open Model Suite for Scaling Robotics Data Engines 2 upvotes, #44 of 2026-10-26

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.