Daily Papers of 2023-12-07

  1. Kandinsky 3.0 Technical Report 45 upvotes, #1 of 2023-12-07
  2. Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis 34 upvotes, #2 of 2023-12-07
  3. Alpha-CLIP: A CLIP Model Focusing on Wherever You Want 33 upvotes, #3 of 2023-12-07
  4. Chain of Code: Reasoning with a Language Model-Augmented Code Emulator 33 upvotes, #3 of 2023-12-07
  5. Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians 26 upvotes, #5 of 2023-12-07
  6. MotionCtrl: A Unified and Flexible Motion Controller for Video Generation 21 upvotes, #6 of 2023-12-07
  7. Beyond Surface: Probing LLaMA Across Scales and Layers 19 upvotes, #7 of 2023-12-07
  8. HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting 16 upvotes, #8 of 2023-12-07
  9. Context Diffusion: In-Context Aware Image Generation 15 upvotes, #9 of 2023-12-07
  10. Large Language Models for Mathematicians 12 upvotes, #10 of 2023-12-07
  11. MagicStick: Controllable Video Editing via Control Handle Transformations 10 upvotes, #11 of 2023-12-07
  12. DreamComposer: Controllable 3D Object Generation via Multi-View Conditions 8 upvotes, #12 of 2023-12-07
  13. Self-conditioned Image Generation via Generating Representations 8 upvotes, #12 of 2023-12-07
  14. Generating Illustrated Instructions 8 upvotes, #12 of 2023-12-07
  15. HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces 7 upvotes, #15 of 2023-12-07
  16. LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning 7 upvotes, #15 of 2023-12-07
  17. Efficient Monotonic Multihead Attention 7 upvotes, #15 of 2023-12-07

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.