Daily Papers of 2025-08-20

  1. Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL 114 upvotes, #1 of 2025-08-20
  2. LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos 55 upvotes, #2 of 2025-08-20
  3. Prompt Orchestration Markup Language 42 upvotes, #3 of 2025-08-20
  4. MultiRef: Controllable Image Generation with Multiple Visual References 20 upvotes, #4 of 2025-08-20
  5. Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer 16 upvotes, #5 of 2025-08-20
  6. MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents 16 upvotes, #5 of 2025-08-20
  7. OmniTry: Virtual Try-On Anything without Masks 16 upvotes, #5 of 2025-08-20
  8. Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation 15 upvotes, #8 of 2025-08-20
  9. Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge 14 upvotes, #9 of 2025-08-20
  10. Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation 13 upvotes, #10 of 2025-08-20
  11. Leveraging Large Language Models for Predictive Analysis of Human Misery 13 upvotes, #10 of 2025-08-20
  12. Advances in Speech Separation: Techniques, Challenges, and Future Trends 12 upvotes, #12 of 2025-08-20
  13. TempFlow-GRPO: When Timing Matters for GRPO in Flow Models 10 upvotes, #13 of 2025-08-20
  14. A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models 10 upvotes, #13 of 2025-08-20
  15. CAMAR: Continuous Actions Multi-Agent Routing 6 upvotes, #15 of 2025-08-20
  16. Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations 5 upvotes, #16 of 2025-08-20
  17. Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends 5 upvotes, #16 of 2025-08-20
  18. Semantic IDs for Joint Generative Search and Recommendation 4 upvotes, #18 of 2025-08-20
  19. Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward 4 upvotes, #18 of 2025-08-20
  20. MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence 4 upvotes, #18 of 2025-08-20
  21. Retrieval-augmented reasoning with lean language models 3 upvotes, #21 of 2025-08-20
  22. Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence 3 upvotes, #21 of 2025-08-20
  23. Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research 2 upvotes, #23 of 2025-08-20
  24. MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation 2 upvotes, #23 of 2025-08-20
  25. CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection 2 upvotes, #23 of 2025-08-20
  26. Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding 2 upvotes, #23 of 2025-08-20
  27. ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents 1 upvotes, #27 of 2025-08-20
  28. Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts 1 upvotes, #27 of 2025-08-20

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.