Rate My Professor Zhenghao Chen

Dr. Chen's research interests lie broadly in Generative AI (GenAI), with specific emphases on computer vision (30%), deep learning (30%), multimodal analysis and synthesis (20%), and natural language processing (20%). He has published extensively at flagship conferences including CVPR, ICCV, ICLR, ECCV, MM, and AAAI, and in top journals such as T-IP, T-PAMI, T-MI, and PR. Key publications include 'Neural Video Compression with Spatio-Temporal Cross-Covariance Transformers' (2023), 'LSVC: A Learning-based Stereo Video Compression Framework' (2022), '3D Gaussian Splatting Data Compression with Mixture of Priors' (2025), 'Medxchat: A Unified Multimodal Large Language Model Framework Towards CXRS Understanding and Generation' (2025), and 'Frame-Voyager: Learning to Query Frames for Video Large Language Models' (2025). He serves on program committees for CVPR, ECCV, ICCV, SIGGRAPH, AAAI, IJCAI, MICCAI, MM, and KDD, reviews for T-IP, T-MI, T-CSVT, IJCV, PR, and acts as Guest Editor for MTAP, MDPI-Algorithms, and Frontiers-in-AI. Through roles at Microsoft, TikTok, and Disney Research, his innovations have resulted in multiple patents and deployments in global enterprise GenAI systems, while interdisciplinary collaborations feature in Nature Portfolio journals.