Daily Papers of 2023-10-20

  1. 3D-GPT: Procedural 3D Modeling with Large Language Models 61 upvotes, #1 of 2023-10-20
  2. AgentTuning: Enabling Generalized Agent Abilities for LLMs 36 upvotes, #2 of 2023-10-20
  3. Safe RLHF: Safe Reinforcement Learning from Human Feedback 28 upvotes, #3 of 2023-10-20
  4. Eureka: Human-Level Reward Design via Coding Large Language Models 26 upvotes, #4 of 2023-10-20
  5. Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning 19 upvotes, #5 of 2023-10-20
  6. Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing 14 upvotes, #6 of 2023-10-20
  7. AutoMix: Automatically Mixing Language Models 14 upvotes, #6 of 2023-10-20
  8. An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning 13 upvotes, #8 of 2023-10-20
  9. An Emulator for Fine-Tuning Large Language Models using Small Language Models 13 upvotes, #8 of 2023-10-20
  10. Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping 5 upvotes, #10 of 2023-10-20

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.