Daily Papers of 2024-01-03

  1. DocLLM: A layout-aware generative language model for multimodal document understanding 192 upvotes, #1 of 2024-01-03
  2. Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models 69 upvotes, #2 of 2024-01-03
  3. LLaMA Beyond English: An Empirical Study on Language Capability Transfer 54 upvotes, #3 of 2024-01-03
  4. LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning 27 upvotes, #4 of 2024-01-03
  5. VideoDrafter: Content-Consistent Multi-Scene Video Generation with LLM 21 upvotes, #5 of 2024-01-03
  6. A Comprehensive Study of Knowledge Editing for Large Language Models 19 upvotes, #6 of 2024-01-03
  7. Boundary Attention: Learning to Find Faint Boundaries at Any Resolution 17 upvotes, #7 of 2024-01-03
  8. TrailBlazer: Trajectory Control for Diffusion-Based Video Generation 14 upvotes, #8 of 2024-01-03
  9. En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data 11 upvotes, #9 of 2024-01-03
  10. Taming Mode Collapse in Score Distillation for Text-to-3D Generation 9 upvotes, #10 of 2024-01-03
  11. Q-Refine: A Perceptual Quality Refiner for AI-Generated Image 8 upvotes, #11 of 2024-01-03

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.