Daily Papers of 2025-01-15

  1. MiniMax-01: Scaling Foundation Models with Lightning Attention 267 upvotes, #1 of 2025-01-15
  2. MangaNinja: Line Art Colorization with Precise Reference Following 55 upvotes, #2 of 2025-01-15
  3. 3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering 33 upvotes, #3 of 2025-01-15
  4. Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models 31 upvotes, #4 of 2025-01-15
  5. Diffusion Adversarial Post-Training for One-Step Video Generation 31 upvotes, #4 of 2025-01-15
  6. Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks 31 upvotes, #4 of 2025-01-15
  7. A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following 24 upvotes, #7 of 2025-01-15
  8. FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors 17 upvotes, #8 of 2025-01-15
  9. Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens 16 upvotes, #9 of 2025-01-15
  10. HALoGEN: Fantastic LLM Hallucinations and Where to Find Them 16 upvotes, #9 of 2025-01-15
  11. Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding 13 upvotes, #11 of 2025-01-15
  12. PokerBench: Training Large Language Models to become Professional Poker Players 13 upvotes, #11 of 2025-01-15
  13. Enhancing Automated Interpretability with Output-Centric Feature Descriptions 10 upvotes, #13 of 2025-01-15
  14. OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training 7 upvotes, #14 of 2025-01-15
  15. Potential and Perils of Large Language Models as Judges of Unstructured Textual Data 6 upvotes, #15 of 2025-01-15
  16. AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages 6 upvotes, #15 of 2025-01-15
  17. MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training 5 upvotes, #17 of 2025-01-15
  18. In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR 4 upvotes, #18 of 2025-01-15

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.