Daily Papers of 2025-05-07

  1. Absolute Zero: Reinforced Self-play Reasoning with Zero Data 135 upvotes, #1 of 2025-05-07
  2. Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning 87 upvotes, #2 of 2025-05-07
  3. RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale 27 upvotes, #3 of 2025-05-07
  4. FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios 25 upvotes, #4 of 2025-05-07
  5. An Empirical Study of Qwen3 Quantization 23 upvotes, #5 of 2025-05-07
  6. RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference 23 upvotes, #5 of 2025-05-07
  7. Multi-Agent System for Comprehensive Soccer Understanding 20 upvotes, #7 of 2025-05-07
  8. HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation 15 upvotes, #8 of 2025-05-07
  9. Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading 15 upvotes, #8 of 2025-05-07
  10. SWE-smith: Scaling Data for Software Engineering Agents 10 upvotes, #10 of 2025-05-07
  11. Geospatial Mechanistic Interpretability of Large Language Models 9 upvotes, #11 of 2025-05-07
  12. VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model 8 upvotes, #12 of 2025-05-07
  13. Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation 7 upvotes, #13 of 2025-05-07
  14. Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems 6 upvotes, #14 of 2025-05-07
  15. InfoVids: Reimagining the Viewer Experience with Alternative Visualization-Presenter Relationships 5 upvotes, #15 of 2025-05-07
  16. Teaching Models to Understand (but not Generate) High-risk Data 4 upvotes, #16 of 2025-05-07
  17. Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant 2 upvotes, #17 of 2025-05-07
  18. Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering 2 upvotes, #17 of 2025-05-07
  19. Alpha Excel Benchmark 2 upvotes, #19 of 2025-05-07

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.