Daily Papers of 2025-01-24

  1. SRMT: Shared Memory for Multi-agent Lifelong Pathfinding 62 upvotes, #1 of 2025-01-24
  2. Improving Video Generation with Human Feedback 44 upvotes, #2 of 2025-01-24
  3. Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models 40 upvotes, #3 of 2025-01-24
  4. Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step 31 upvotes, #4 of 2025-01-24
  5. Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos 22 upvotes, #5 of 2025-01-24
  6. Temporal Preference Optimization for Long-Form Video Understanding 21 upvotes, #6 of 2025-01-24
  7. Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback 14 upvotes, #7 of 2025-01-24
  8. DiffuEraser: A Diffusion Model for Video Inpainting 13 upvotes, #8 of 2025-01-24
  9. IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models 13 upvotes, #8 of 2025-01-24
  10. One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt 9 upvotes, #10 of 2025-01-24
  11. Hallucinations Can Improve Large Language Models in Drug Discovery 8 upvotes, #11 of 2025-01-24
  12. EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion 7 upvotes, #12 of 2025-01-24
  13. Control LLM: Controlled Evolution for Intelligence Retention in LLM 6 upvotes, #13 of 2025-01-24
  14. Evolution and The Knightian Blindspot of Machine Learning 6 upvotes, #13 of 2025-01-24
  15. Debate Helps Weak-to-Strong Generalization 6 upvotes, #13 of 2025-01-24
  16. EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents 5 upvotes, #16 of 2025-01-24
  17. GSTAR: Gaussian Surface Tracking and Reconstruction 4 upvotes, #17 of 2025-01-24

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.