Daily Papers of 2025-05-13

  1. Seed1.5-VL Technical Report 136 upvotes, #1 of 2025-05-13
  2. MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining 74 upvotes, #2 of 2025-05-13
  3. Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets 60 upvotes, #3 of 2025-05-13
  4. Learning from Peers in Reasoning Models 41 upvotes, #4 of 2025-05-13
  5. Unified Continuous Generative Models 38 upvotes, #5 of 2025-05-13
  6. Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning 29 upvotes, #6 of 2025-05-13
  7. REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback 27 upvotes, #7 of 2025-05-13
  8. DanceGRPO: Unleashing GRPO on Visual Generation 27 upvotes, #7 of 2025-05-13
  9. AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection 25 upvotes, #9 of 2025-05-13
  10. Learning Dynamics in Continual Pre-Training for Large Language Models 18 upvotes, #10 of 2025-05-13
  11. WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch 16 upvotes, #11 of 2025-05-13
  12. Continuous Visual Autoregressive Generation via Score Maximization 11 upvotes, #12 of 2025-05-13
  13. MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills 10 upvotes, #13 of 2025-05-13
  14. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning 10 upvotes, #13 of 2025-05-13
  15. Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent 10 upvotes, #13 of 2025-05-13
  16. Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation 9 upvotes, #16 of 2025-05-13
  17. UMoE: Unifying Attention and FFN with Shared Experts 8 upvotes, #17 of 2025-05-13
  18. DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation 7 upvotes, #18 of 2025-05-13
  19. LLAMAPIE: Proactive In-Ear Conversation Assistants 5 upvotes, #19 of 2025-05-13
  20. H^{3}DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning 5 upvotes, #19 of 2025-05-13
  21. Document Attribution: Examining Citation Relationships using Large Language Models 3 upvotes, #21 of 2025-05-13
  22. Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction 2 upvotes, #22 of 2025-05-13
  23. Overflow Prevention Enhances Long-Context Recurrent LLMs 2 upvotes, #22 of 2025-05-13
  24. Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design 1 upvotes, #24 of 2025-05-13

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.