CFG-Zero*: Classifier-Free Guidance with Zero Prediction (arXiv, 2025)
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models (arXiv, 2025)
RepVideo: Rethinking Cross-Layer Representation for Video Generation (arXiv, 2025)
Link-Context Learning For Multimodal LLMs (CVPR, 2024)
Hierarchy Flow For High-Fidelity Image-to-Image Translation (arXiv, 2022)
SAVAnet: Surgical Action-Driven Visual Attention Network for Autonomous Endoscope Control (IEEE Transactions on Automation Science and Engineering, 2022)
Education
Bachelor's degree: University of Electronic Science and Technology of China (UESTC); Master's degree: National University of Singapore (NUS); PhD: Nanyang Technological University, Advisor: Prof. Ziwei Liu.
Background
Research Interests: Video generation, diffusion models, and robotics. Currently a PhD student at MMLab@NTU, supervised by Prof. Ziwei Liu.
Miscellany
Contact: weichen.fan [at] u.nus.edu; GitHub and Google Scholar profiles available