Daily Papers of 2023-10-23

  1. Contrastive Prefence Learning: Learning from Human Feedback without RL 25 upvotes, #1 of 2023-10-23
  2. Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models 19 upvotes, #2 of 2023-10-23
  3. DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics 18 upvotes, #3 of 2023-10-23
  4. SALMONN: Towards Generic Hearing Abilities for Large Language Models 17 upvotes, #4 of 2023-10-23
  5. Democratizing Reasoning Ability: Tailored Learning from Large Language Model 16 upvotes, #5 of 2023-10-23
  6. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search 15 upvotes, #6 of 2023-10-23
  7. DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation 13 upvotes, #7 of 2023-10-23
  8. Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models 12 upvotes, #8 of 2023-10-23
  9. Teaching Language Models to Self-Improve through Interactive Demonstrations 12 upvotes, #8 of 2023-10-23
  10. Creative Robot Tool Use with Large Language Models 10 upvotes, #10 of 2023-10-23
  11. Tuna: Instruction Tuning using Feedback from Large Language Models 10 upvotes, #10 of 2023-10-23
  12. H2O Open Ecosystem for State-of-the-art Large Language Models 9 upvotes, #12 of 2023-10-23
  13. SILC: Improving Vision Language Pretraining with Self-Distillation 9 upvotes, #12 of 2023-10-23
  14. Towards Understanding Sycophancy in Language Models 7 upvotes, #14 of 2023-10-23
  15. ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection 4 upvotes, #15 of 2023-10-23

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.