Cong Wang

Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization

Steering When Necessary: Flexible Steering Large Language Models with Backtracking

Ensembling Diffusion Models via Adaptive Feature Aggregation

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models