Daily Papers of 2023-12-22

  1. AppAgent: Multimodal Agents as Smartphone Users 54 upvotes, #1 of 2023-12-22
  2. VideoPoet: A Large Language Model for Zero-Shot Video Generation 47 upvotes, #2 of 2023-12-22
  3. DREAM-Talk: Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation 29 upvotes, #3 of 2023-12-22
  4. DreamTuner: Single Image is Enough for Subject-Driven Generation 27 upvotes, #4 of 2023-12-22
  5. Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis 26 upvotes, #5 of 2023-12-22
  6. Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models 23 upvotes, #6 of 2023-12-22
  7. Time is Encoded in the Weights of Finetuned Language Models 20 upvotes, #7 of 2023-12-22
  8. PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models 19 upvotes, #8 of 2023-12-22
  9. HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models 17 upvotes, #9 of 2023-12-22
  10. TinySAM: Pushing the Envelope for Efficient Segment Anything Model 14 upvotes, #10 of 2023-12-22
  11. Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning 14 upvotes, #10 of 2023-12-22
  12. Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation 11 upvotes, #12 of 2023-12-22
  13. ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors 10 upvotes, #13 of 2023-12-22
  14. Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models 10 upvotes, #13 of 2023-12-22
  15. Unlocking Pre-trained Image Backbones for Semantic Image Synthesis 8 upvotes, #15 of 2023-12-22
  16. DyBluRF: Dynamic Deblurring Neural Radiance Fields for Blurry Monocular Video 7 upvotes, #16 of 2023-12-22
  17. HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs 7 upvotes, #16 of 2023-12-22

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.