Daily Papers of 2025-02-13

  1. BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models 48 upvotes, #1 of 2025-02-13
  2. Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance 48 upvotes, #1 of 2025-02-13
  3. TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation 42 upvotes, #3 of 2025-02-13
  4. TransMLA: Multi-head Latent Attention Is All You Need 41 upvotes, #4 of 2025-02-13
  5. Distillation Scaling Laws 40 upvotes, #5 of 2025-02-13
  6. Light-A-Video: Training-free Video Relighting via Progressive Light Fusion 37 upvotes, #6 of 2025-02-13
  7. CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation 36 upvotes, #7 of 2025-02-13
  8. WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation 24 upvotes, #8 of 2025-02-13
  9. LLM Pretraining with Continuous Concepts 24 upvotes, #8 of 2025-02-13
  10. LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid 23 upvotes, #10 of 2025-02-13
  11. Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning 17 upvotes, #11 of 2025-02-13
  12. PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs 16 upvotes, #12 of 2025-02-13
  13. Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance 16 upvotes, #12 of 2025-02-13
  14. NoLiMa: Long-Context Evaluation Beyond Literal Matching 14 upvotes, #14 of 2025-02-13
  15. DPO-Shift: Shifting the Distribution of Direct Preference Optimization 14 upvotes, #14 of 2025-02-13
  16. SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation 10 upvotes, #16 of 2025-02-13
  17. Next Block Prediction: Video Generation via Semi-Autoregressive Modeling 9 upvotes, #17 of 2025-02-13
  18. Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey 8 upvotes, #18 of 2025-02-13
  19. Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing 4 upvotes, #19 of 2025-02-13
  20. LLM Modules: Knowledge Transfer from a Large to a Small Model using Enhanced Cross-Attention 4 upvotes, #19 of 2025-02-13
  21. MetaSC: Test-Time Safety Specification Optimization for Language Models 3 upvotes, #21 of 2025-02-13
  22. Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning 0 upvotes, #22 of 2025-02-13

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.