Daily Papers of 2023-11-22

1. MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer 31 upvotes, #1 of 2023-11-22
2. HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis 30 upvotes, #2 of 2023-11-22
3. SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering 30 upvotes, #2 of 2023-11-22
4. NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation 25 upvotes, #4 of 2023-11-22
5. Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models 22 upvotes, #5 of 2023-11-22
6. PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics 21 upvotes, #6 of 2023-11-22
7. PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction 19 upvotes, #7 of 2023-11-22
8. GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning 14 upvotes, #8 of 2023-11-22

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.