Daily Papers of 2025-11-21

  1. Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning 96 upvotes, #1 of 2025-11-21
  2. SAM 3D: 3Dfy Anything in Images 95 upvotes, #2 of 2025-11-21
  3. V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models 52 upvotes, #3 of 2025-11-21
  4. First Frame Is the Place to Go for Video Content Customization 51 upvotes, #4 of 2025-11-21
  5. Step-Audio-R1 Technical Report 51 upvotes, #4 of 2025-11-21
  6. Scaling Spatial Intelligence with Multimodal Foundation Models 41 upvotes, #6 of 2025-11-21
  7. Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO 31 upvotes, #7 of 2025-11-21
  8. MiMo-Embodied: X-Embodied Foundation Model Technical Report 23 upvotes, #8 of 2025-11-21
  9. SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models 22 upvotes, #9 of 2025-11-21
  10. Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs 22 upvotes, #9 of 2025-11-21
  11. Generalist Foundation Models Are Not Clinical Enough for Hospital Operations 20 upvotes, #11 of 2025-11-21
  12. NaTex: Seamless Texture Generation as Latent Color Diffusion 15 upvotes, #12 of 2025-11-21
  13. TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval 15 upvotes, #12 of 2025-11-21
  14. Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation 15 upvotes, #12 of 2025-11-21
  15. TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding 9 upvotes, #15 of 2025-11-21
  16. PartUV: Part-Based UV Unwrapping of 3D Meshes 8 upvotes, #16 of 2025-11-21
  17. SAM2S: Segment Anything in Surgical Videos via Semantic Long-term Tracking 7 upvotes, #17 of 2025-11-21
  18. EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control 5 upvotes, #18 of 2025-11-21
  19. FinTRec: Transformer Based Unified Contextual Ads Targeting and Personalization for Financial Applications 3 upvotes, #19 of 2025-11-21
  20. Draft and Refine with Visual Experts 2 upvotes, #20 of 2025-11-21
  21. BioBench: A Blueprint to Move Beyond ImageNet for Scientific ML Benchmarks 2 upvotes, #20 of 2025-11-21
  22. Boosting Medical Visual Understanding From Multi-Granular Language Learning 1 upvotes, #22 of 2025-11-21

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.