Published multiple papers, including those accepted by top conferences like ICCV, CVPR, and ECCV; received several awards, such as being recognized as one of the Outstanding Reviewers for CVPR 2025 and winning the Outstanding Graduates of Shanghai; involved in research projects that ranked first on the VDC leaderboard.
Research Experience
Involved in multiple research projects, including FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers (as Research Project Lead) and Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption (as Co-lead).
Education
Received a B.S. from the Department of Computer Science and Technology at ECUST in July 2019; obtained a Ph.D. degree from ECUST from September 2019 to June 2024.
Background
Research interests include multi-modal learning/AIGC, such as content generation of 2D images and videos using Generative Adversarial Networks, Diffusion, and auto-regressive models. Aiming to contribute to fundamental research and application-related problems in multi-modal learning and generative models.
Miscellany
Personal blogs cover topics related to multi-modal learning and visual generation, with random thoughts shared on the tinymind platform.