Tao Mei

ReactID: Synchronizing Realistic Actions and Identity in Personalized Video Generation

Visual Autoregressive Modeling for Instruction-Guided Image Editing

VTON-VLLM: Aligning Virtual Try-On Models with Human Preferences

Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots

Region-wise Motion Controller for Image-to-Video Generation