My research interests cover content generation and cross-modality representation learning, especially for image, video and audio synthesis.
Prior to that, I was a senior researcher at Tencent since 2020. I obtained the master's degree from Institute of Automation, Chinese Academy of Sciences.
Before that, I received the bachelor's degree from Northeastern University with honors in 2017.
Selected Publications
MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation
ACM MM 2024 / Paper
Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection
ECCV 2024 / Paper
Honors and Awards