Daily Papers of 2023-12-18

  1. Amphion: An Open-Source Audio, Music and Speech Generation Toolkit 54 upvotes, #1 of 2023-12-18
  2. ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent 43 upvotes, #2 of 2023-12-18
  3. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision 33 upvotes, #3 of 2023-12-18
  4. DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models 25 upvotes, #4 of 2023-12-18
  5. MobileSAMv2: Faster Segment Anything to Everything 24 upvotes, #5 of 2023-12-18
  6. Point Transformer V3: Simpler, Faster, Stronger 21 upvotes, #6 of 2023-12-18
  7. Weight subcloning: direct initialization of transformers using larger pretrained ones 18 upvotes, #7 of 2023-12-18
  8. Self-Evaluation Improves Selective Generation in Large Language Models 15 upvotes, #8 of 2023-12-18
  9. Extending Context Window of Large Language Models via Semantic Compression 14 upvotes, #9 of 2023-12-18
  10. Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models 14 upvotes, #9 of 2023-12-18
  11. Faithful Persona-based Conversational Dataset Generation with Large Language Models 9 upvotes, #11 of 2023-12-18
  12. Stable Score Distillation for High-Quality 3D Generation 8 upvotes, #12 of 2023-12-18
  13. Challenges with unsupervised LLM knowledge discovery 8 upvotes, #12 of 2023-12-18
  14. SlimmeRF: Slimmable Radiance Fields 7 upvotes, #14 of 2023-12-18
  15. Perspectives on the State and Future of Deep Learning -- 2023 6 upvotes, #15 of 2023-12-18

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.