X-Dancer: Expressive Music to Human Dance Video Generation (ICCV, 2025)
X-Dyna: Expressive Dynamic Human Image Animation (CVPR, 2025)
MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-based Emotional Talking Face Generation (CVM, 2025)
X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention (SIGGRAPH 2024)
DR2: Disentangled Recurrent Representation Learning for Data-efficient Speech Video Synthesis (WACV, 2024)
Using Augmented Face Images to Improve Facial Recognition Tasks (CHI Workshop, 2022)
Study of detecting behavioral signatures within DeepFake videos (Arxiv Preprint, 2022)
Efficient Plane-Based Optimization of Geometry and Texture for Indoor RGB-D Reconstruction (CVPR Workshops, 2019)
Background
Current research interests are mainly in the areas of computer vision and graphics, specifically in talking head generation, human video generation, multi-modal motion synthesis, and generative modeling.