Daily Papers of 2025-04-30

  1. Reinforcement Learning for Reasoning in Large Language Models with One Training Example 88 upvotes, #1 of 2025-04-30
  2. The Leaderboard Illusion 66 upvotes, #2 of 2025-04-30
  3. UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities 60 upvotes, #3 of 2025-04-30
  4. ReasonIR: Training Retrievers for Reasoning Tasks 50 upvotes, #4 of 2025-04-30
  5. Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models 34 upvotes, #5 of 2025-04-30
  6. TesserAct: Learning 4D Embodied World Models 19 upvotes, #6 of 2025-04-30
  7. In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer 16 upvotes, #7 of 2025-04-30
  8. Certified Mitigation of Worst-Case LLM Copyright Infringement 12 upvotes, #8 of 2025-04-30
  9. X-Fusion: Introducing New Modality to Frozen Large Language Models 11 upvotes, #9 of 2025-04-30
  10. YoChameleon: Personalized Vision and Language Generation 11 upvotes, #9 of 2025-04-30
  11. RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning 8 upvotes, #11 of 2025-04-30
  12. ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting 8 upvotes, #11 of 2025-04-30
  13. Learning Explainable Dense Reward Shapes via Bayesian Optimization 5 upvotes, #13 of 2025-04-30
  14. TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering 5 upvotes, #13 of 2025-04-30
  15. Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation 4 upvotes, #15 of 2025-04-30
  16. LawFlow : Collecting and Simulating Lawyers' Thought Processes 4 upvotes, #15 of 2025-04-30
  17. Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption 3 upvotes, #17 of 2025-04-30
  18. CaRL: Learning Scalable Planning Policies with Simple Rewards 2 upvotes, #18 of 2025-04-30
  19. A Review of 3D Object Detection with Vision-Language Models 2 upvotes, #18 of 2025-04-30

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.