Daily Papers of 2025-03-10

  1. RuCCoD: Towards Automated ICD Coding in Russian 122 upvotes, #1 of 2025-03-10
  2. Unified Reward Model for Multimodal Understanding and Generation 105 upvotes, #2 of 2025-03-10
  3. EuroBERT: Scaling Multilingual Encoders for European Languages 72 upvotes, #3 of 2025-03-10
  4. R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model 49 upvotes, #4 of 2025-03-10
  5. S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information 45 upvotes, #5 of 2025-03-10
  6. Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching 42 upvotes, #6 of 2025-03-10
  7. R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning 32 upvotes, #7 of 2025-03-10
  8. Forgetting Transformer: Softmax Attention with a Forget Gate 27 upvotes, #8 of 2025-03-10
  9. R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning 25 upvotes, #9 of 2025-03-10
  10. VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control 21 upvotes, #10 of 2025-03-10
  11. SafeArena: Evaluating the Safety of Autonomous Web Agents 18 upvotes, #11 of 2025-03-10
  12. Learning from Failures in Multi-Attempt Reinforcement Learning 17 upvotes, #12 of 2025-03-10
  13. TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models 17 upvotes, #12 of 2025-03-10
  14. TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation 14 upvotes, #14 of 2025-03-10
  15. LoRACode: LoRA Adapters for Code Embeddings 10 upvotes, #15 of 2025-03-10
  16. BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities 10 upvotes, #15 of 2025-03-10
  17. ProReflow: Progressive Reflow with Decomposed Velocity 9 upvotes, #17 of 2025-03-10
  18. An Empirical Study on Eliciting and Improving R1-like Reasoning Models 8 upvotes, #18 of 2025-03-10
  19. Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts 7 upvotes, #19 of 2025-03-10
  20. LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding 6 upvotes, #20 of 2025-03-10
  21. SAGE: A Framework of Precise Retrieval for RAG 5 upvotes, #21 of 2025-03-10
  22. EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test 4 upvotes, #22 of 2025-03-10
  23. Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles 3 upvotes, #23 of 2025-03-10
  24. AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM 2 upvotes, #24 of 2025-03-10

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.