Daily Papers of 2025-07-09

  1. SingLoRA: Low Rank Adaptation Using a Single Matrix 95 upvotes, #1 of 2025-07-09
  2. A Survey on Latent Reasoning 78 upvotes, #2 of 2025-07-09
  3. OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion 53 upvotes, #3 of 2025-07-09
  4. How to Train Your LLM Web Agent: A Statistical Diagnosis 46 upvotes, #4 of 2025-07-09
  5. StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling 42 upvotes, #5 of 2025-07-09
  6. CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization 38 upvotes, #6 of 2025-07-09
  7. RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents 31 upvotes, #7 of 2025-07-09
  8. MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos 26 upvotes, #8 of 2025-07-09
  9. GTA1: GUI Test-time Scaling Agent 24 upvotes, #9 of 2025-07-09
  10. Critiques of World Models 22 upvotes, #10 of 2025-07-09
  11. Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts 20 upvotes, #11 of 2025-07-09
  12. Coding Triangle: How Does Large Language Model Understand Code? 19 upvotes, #12 of 2025-07-09
  13. Is Diversity All You Need for Scalable Robotic Manipulation? 19 upvotes, #12 of 2025-07-09
  14. Differential Mamba 16 upvotes, #14 of 2025-07-09
  15. MedGemma Technical Report 14 upvotes, #15 of 2025-07-09
  16. Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers 13 upvotes, #16 of 2025-07-09
  17. PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs 11 upvotes, #17 of 2025-07-09
  18. High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning 11 upvotes, #17 of 2025-07-09
  19. SAMed-2: Selective Memory Enhanced Medical Segment Anything Model 10 upvotes, #19 of 2025-07-09
  20. LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework 9 upvotes, #20 of 2025-07-09
  21. Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation 9 upvotes, #20 of 2025-07-09
  22. any4: Learned 4-bit Numeric Representation for LLMs 6 upvotes, #22 of 2025-07-09
  23. The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation 5 upvotes, #23 of 2025-07-09
  24. NeoBabel: A Multilingual Open Tower for Visual Generation 4 upvotes, #24 of 2025-07-09
  25. Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion 3 upvotes, #25 of 2025-07-09
  26. FAROS: Fair Graph Generation via Attribute Switching Mechanisms 1 upvotes, #26 of 2025-07-09
  27. AXLearn: Modular Large Model Training on Heterogeneous Infrastructure 1 upvotes, #26 of 2025-07-09
  28. Does Data Scaling Lead to Visual Compositional Generalization? 1 upvotes, #26 of 2025-07-09

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.