Daily Papers of 2023-12-27

  1. SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling 61 upvotes, #1 of 2023-12-27
  2. Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4 36 upvotes, #2 of 2023-12-27
  3. Make-A-Character: High Quality Text-to-3D Character Generation within Minutes 28 upvotes, #3 of 2023-12-27
  4. UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces 20 upvotes, #4 of 2023-12-27
  5. Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases 18 upvotes, #5 of 2023-12-27
  6. Audiobox: Unified Audio Generation with Natural Language Prompts 15 upvotes, #6 of 2023-12-27
  7. LangSplat: 3D Language Gaussian Splatting 15 upvotes, #6 of 2023-12-27
  8. A Recipe for Scaling up Text-to-Video Generation with Text-free Videos 14 upvotes, #8 of 2023-12-27
  9. Human101: Training 100+FPS Human Gaussians in 100s from 1 View 12 upvotes, #9 of 2023-12-27
  10. HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D 12 upvotes, #9 of 2023-12-27
  11. Supervised Knowledge Makes Large Language Models Better In-context Learners 9 upvotes, #11 of 2023-12-27
  12. One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications 9 upvotes, #11 of 2023-12-27

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.