Daily Papers of 2025-10-30

  1. Scaling Latent Reasoning via Looped Language Models 201 upvotes, #1 of 2025-10-30
  2. JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence 95 upvotes, #2 of 2025-10-30
  3. Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning 83 upvotes, #3 of 2025-10-30
  4. The Principles of Diffusion Models 51 upvotes, #4 of 2025-10-30
  5. ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization 50 upvotes, #5 of 2025-10-30
  6. The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution 44 upvotes, #6 of 2025-10-30
  7. Reasoning-Aware GRPO using Process Mining 41 upvotes, #7 of 2025-10-30
  8. Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation 34 upvotes, #8 of 2025-10-30
  9. VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning 32 upvotes, #9 of 2025-10-30
  10. RegionE: Adaptive Region-Aware Generation for Efficient Image Editing 25 upvotes, #10 of 2025-10-30
  11. ODesign: A World Model for Biomolecular Interaction Design 22 upvotes, #11 of 2025-10-30
  12. ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks 17 upvotes, #12 of 2025-10-30
  13. Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks 16 upvotes, #13 of 2025-10-30
  14. Parallel Loop Transformer for Efficient Test-Time Computation Scaling 14 upvotes, #14 of 2025-10-30
  15. Automating Benchmark Design 14 upvotes, #14 of 2025-10-30
  16. MASPRM: Multi-Agent System Process Reward Model 13 upvotes, #16 of 2025-10-30
  17. PairUni: Pairwise Training for Unified Multimodal Language Models 13 upvotes, #16 of 2025-10-30
  18. Gaperon: A Peppered English-French Generative Language Model Suite 12 upvotes, #18 of 2025-10-30
  19. Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks 10 upvotes, #19 of 2025-10-30
  20. Evolving Diagnostic Agents in a Virtual Clinical Environment 10 upvotes, #19 of 2025-10-30
  21. Reasoning Language Model Inference Serving Unveiled: An Empirical Study 7 upvotes, #21 of 2025-10-30
  22. SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs 7 upvotes, #21 of 2025-10-30
  23. FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning 6 upvotes, #23 of 2025-10-30
  24. The Quest for Reliable Metrics of Responsible AI 3 upvotes, #24 of 2025-10-30
  25. GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research 2 upvotes, #25 of 2025-10-30
  26. Generative View Stitching 2 upvotes, #25 of 2025-10-30
  27. Fortytwo: Swarm Inference with Peer-Ranked Consensus 2 upvotes, #25 of 2025-10-30
  28. MC-SJD : Maximal Coupling Speculative Jacobi Decoding for Autoregressive Visual Generation Acceleration 1 upvotes, #28 of 2025-10-30
  29. BhashaBench V1: A Comprehensive Benchmark for the Quadrant of Indic Domains 1 upvotes, #28 of 2025-10-30
  30. TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling 1 upvotes, #28 of 2025-10-30

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.