Daily Papers of 2025-02-12

  1. Expect the Unexpected: FailSafe Long Context QA for Finance 122 upvotes, #1 of 2025-02-12
  2. Competitive Programming with Large Reasoning Models 59 upvotes, #2 of 2025-02-12
  3. Retrieval-augmented Large Language Models for Financial Time Series Forecasting 38 upvotes, #3 of 2025-02-12
  4. CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction 38 upvotes, #3 of 2025-02-12
  5. Magic 1-For-1: Generating One Minute Video Clips within One Minute 32 upvotes, #5 of 2025-02-12
  6. LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! 31 upvotes, #6 of 2025-02-12
  7. Scaling Pre-training to One Hundred Billion Data for Vision Language Models 25 upvotes, #7 of 2025-02-12
  8. Teaching Language Models to Critique via Reinforcement Learning 22 upvotes, #8 of 2025-02-12
  9. Gemstones: A Model Suite for Multi-Faceted Scaling Laws 22 upvotes, #8 of 2025-02-12
  10. Enhance-A-Video: Better Generated Video for Free 18 upvotes, #10 of 2025-02-12
  11. NatureLM: Deciphering the Language of Nature for Scientific Discovery 17 upvotes, #11 of 2025-02-12
  12. Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training 16 upvotes, #12 of 2025-02-12
  13. VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation 13 upvotes, #13 of 2025-02-12
  14. Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents 10 upvotes, #14 of 2025-02-12
  15. Hypencoder: Hypernetworks for Information Retrieval 10 upvotes, #14 of 2025-02-12
  16. CoS: Chain-of-Shot Prompting for Long Video Understanding 9 upvotes, #16 of 2025-02-12
  17. Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon 9 upvotes, #16 of 2025-02-12
  18. Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More 9 upvotes, #16 of 2025-02-12
  19. Pippo: High-Resolution Multi-View Humans from a Single Image 9 upvotes, #16 of 2025-02-12
  20. CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing 8 upvotes, #20 of 2025-02-12
  21. Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving 8 upvotes, #20 of 2025-02-12
  22. Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models 6 upvotes, #22 of 2025-02-12
  23. Skill Expansion and Composition in Parameter Space 4 upvotes, #23 of 2025-02-12
  24. FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks 3 upvotes, #24 of 2025-02-12
  25. Auditing Prompt Caching in Language Model APIs 3 upvotes, #24 of 2025-02-12
  26. Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models 2 upvotes, #26 of 2025-02-12

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.