Daily Papers of 2025-02-26

  1. OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference 67 upvotes, #1 of 2025-02-26
  2. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution 62 upvotes, #2 of 2025-02-26
  3. SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference 50 upvotes, #3 of 2025-02-26
  4. KV-Edit: Training-Free Image Editing for Precise Background Preservation 32 upvotes, #4 of 2025-02-26
  5. ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation 32 upvotes, #4 of 2025-02-26
  6. Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective 18 upvotes, #6 of 2025-02-26
  7. Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents 17 upvotes, #7 of 2025-02-26
  8. K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs 15 upvotes, #8 of 2025-02-26
  9. Introducing Visual Perception Token into Multimodal Large Language Model 14 upvotes, #9 of 2025-02-26
  10. Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models 13 upvotes, #10 of 2025-02-26
  11. WebGames: Challenging General-Purpose Web-Browsing AI Agents 10 upvotes, #11 of 2025-02-26
  12. The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve? 8 upvotes, #12 of 2025-02-26
  13. Prompt-to-Leaderboard 7 upvotes, #13 of 2025-02-26
  14. MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs 7 upvotes, #13 of 2025-02-26
  15. Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization 6 upvotes, #15 of 2025-02-26
  16. AAD-LLM: Neural Attention-Driven Auditory Scene Understanding 5 upvotes, #16 of 2025-02-26
  17. LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models 4 upvotes, #17 of 2025-02-26
  18. An Overview of Large Language Models for Statisticians 4 upvotes, #17 of 2025-02-26
  19. LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation 4 upvotes, #17 of 2025-02-26
  20. Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI 3 upvotes, #20 of 2025-02-26
  21. WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging 2 upvotes, #21 of 2025-02-26
  22. Scaling LLM Pre-training with Vocabulary Curriculum 1 upvotes, #22 of 2025-02-26

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.