Daily Papers of 2025-02-28

  1. Self-rewarding correction for mathematical reasoning 75 upvotes, #1 of 2025-02-28
  2. MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning 56 upvotes, #2 of 2025-02-28
  3. R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts 43 upvotes, #3 of 2025-02-28
  4. NeoBERT: A Next-Generation BERT 38 upvotes, #4 of 2025-02-28
  5. LongRoPE2: Near-Lossless LLM Context Window Scaling 31 upvotes, #5 of 2025-02-28
  6. UniTok: A Unified Tokenizer for Visual Generation and Understanding 27 upvotes, #6 of 2025-02-28
  7. Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think 26 upvotes, #7 of 2025-02-28
  8. FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving 24 upvotes, #8 of 2025-02-28
  9. CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale 21 upvotes, #9 of 2025-02-28
  10. FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute 19 upvotes, #10 of 2025-02-28
  11. Mobius: Text to Seamless Looping Video Generation via Latent Shift 16 upvotes, #11 of 2025-02-28
  12. Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation 14 upvotes, #12 of 2025-02-28
  13. Guardians of the Agentic System: Preventing Many Shots Jailbreak with Agentic System 10 upvotes, #13 of 2025-02-28
  14. Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance 10 upvotes, #13 of 2025-02-28
  15. SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning 9 upvotes, #15 of 2025-02-28
  16. Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting 8 upvotes, #16 of 2025-02-28
  17. PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving 7 upvotes, #17 of 2025-02-28
  18. R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning 7 upvotes, #17 of 2025-02-28
  19. On Relation-Specific Neurons in Large Language Models 6 upvotes, #19 of 2025-02-28
  20. Training Consistency Models with Variational Noise Coupling 5 upvotes, #20 of 2025-02-28
  21. Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling 4 upvotes, #21 of 2025-02-28

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.