Daily Papers of 2025-06-25

  1. JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent 59 upvotes, #1 of 2025-06-25
  2. Matrix-Game: Interactive World Foundation Model 58 upvotes, #2 of 2025-06-25
  3. MMSearch-R1: Incentivizing LMMs to Search 56 upvotes, #3 of 2025-06-25
  4. AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models 52 upvotes, #4 of 2025-06-25
  5. Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs 49 upvotes, #5 of 2025-06-25
  6. Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models 39 upvotes, #6 of 2025-06-25
  7. GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning 26 upvotes, #7 of 2025-06-25
  8. ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing 25 upvotes, #8 of 2025-06-25
  9. Unified Vision-Language-Action Model 21 upvotes, #9 of 2025-06-25
  10. SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications 19 upvotes, #10 of 2025-06-25
  11. Can Large Language Models Capture Human Annotator Disagreements? 16 upvotes, #11 of 2025-06-25
  12. Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales 12 upvotes, #12 of 2025-06-25
  13. SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning 12 upvotes, #12 of 2025-06-25
  14. USAD: Universal Speech and Audio Representation via Distillation 11 upvotes, #14 of 2025-06-25
  15. Scaling Speculative Decoding with Lookahead Reasoning 11 upvotes, #14 of 2025-06-25
  16. SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution 11 upvotes, #14 of 2025-06-25
  17. Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text 9 upvotes, #17 of 2025-06-25
  18. Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study 8 upvotes, #18 of 2025-06-25
  19. KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality 6 upvotes, #19 of 2025-06-25
  20. Improving Progressive Generation with Decomposable Flow Matching 6 upvotes, #19 of 2025-06-25
  21. Orthogonal Finetuning Made Scalable 6 upvotes, #19 of 2025-06-25
  22. Intelligent Operation and Maintenance and Prediction Model Optimization for Improving Wind Power Generation Efficiency 4 upvotes, #22 of 2025-06-25
  23. Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System 3 upvotes, #23 of 2025-06-25

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.