Daily Papers of 2023-11-15

  1. Instant3D: Instant Text-to-3D Generation 47 upvotes, #1 of 2023-11-15
  2. One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion 40 upvotes, #2 of 2023-11-15
  3. Fine-tuning Language Models for Factuality 30 upvotes, #3 of 2023-11-15
  4. A Survey on Language Models for Code 26 upvotes, #4 of 2023-11-15
  5. Instruction-Following Evaluation for Large Language Models 22 upvotes, #5 of 2023-11-15
  6. Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure 17 upvotes, #6 of 2023-11-15
  7. DiLoCo: Distributed Low-Communication Training of Language Models 16 upvotes, #7 of 2023-11-15
  8. Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster 16 upvotes, #7 of 2023-11-15
  9. The ART of LLM Refinement: Ask, Refine, and Trust 11 upvotes, #9 of 2023-11-15
  10. MART: Improving LLM Safety with Multi-round Automatic Red-Teaming 9 upvotes, #10 of 2023-11-15
  11. Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models 9 upvotes, #10 of 2023-11-15
  12. Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5? 4 upvotes, #12 of 2023-11-15

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.