Daily Papers of 2025-07-04

  1. WebSailor: Navigating Super-human Reasoning for Web Agent 90 upvotes, #1 of 2025-07-04
  2. Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers 76 upvotes, #2 of 2025-07-04
  3. LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion 55 upvotes, #3 of 2025-07-04
  4. Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy 49 upvotes, #4 of 2025-07-04
  5. Energy-Based Transformers are Scalable Learners and Thinkers 45 upvotes, #5 of 2025-07-04
  6. Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback 38 upvotes, #6 of 2025-07-04
  7. IntFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction 35 upvotes, #7 of 2025-07-04
  8. Fast and Simplex: 2-Simplicial Attention in Triton 23 upvotes, #8 of 2025-07-04
  9. Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search 22 upvotes, #9 of 2025-07-04
  10. Can LLMs Identify Critical Limitations within Scientific Research? A Systematic Evaluation on AI Research Papers 18 upvotes, #10 of 2025-07-04
  11. Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving 14 upvotes, #11 of 2025-07-04
  12. ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention 10 upvotes, #12 of 2025-07-04
  13. Self-Correction Bench: Revealing and Addressing the Self-Correction Blind Spot in LLMs 9 upvotes, #13 of 2025-07-04
  14. Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models 7 upvotes, #14 of 2025-07-04
  15. AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training 5 upvotes, #15 of 2025-07-04
  16. HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation 2 upvotes, #16 of 2025-07-04
  17. CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation 2 upvotes, #16 of 2025-07-04

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.