Daily Papers of 2024-09-20

  1. Training Language Models to Self-Correct via Reinforcement Learning 117 upvotes, #1 of 2024-09-20
  2. InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning 44 upvotes, #2 of 2024-09-20
  3. MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines 33 upvotes, #3 of 2024-09-20
  4. B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests 25 upvotes, #4 of 2024-09-20
  5. Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution 22 upvotes, #5 of 2024-09-20
  6. LVCD: Reference-based Lineart Video Colorization with Diffusion Models 20 upvotes, #6 of 2024-09-20
  7. Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization 19 upvotes, #7 of 2024-09-20
  8. 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion 17 upvotes, #8 of 2024-09-20
  9. StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation 14 upvotes, #9 of 2024-09-20
  10. FlexiTex: Enhancing Texture Generation with Visual Guidance 9 upvotes, #10 of 2024-09-20
  11. Language Models Learn to Mislead Humans via RLHF 8 upvotes, #11 of 2024-09-20
  12. MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions 6 upvotes, #12 of 2024-09-20
  13. Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation 5 upvotes, #13 of 2024-09-20
  14. 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt 5 upvotes, #13 of 2024-09-20
  15. CLAIR-A: Leveraging Large Language Models to Judge Audio Captions 2 upvotes, #15 of 2024-09-20

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.