Contributed to significant research projects such as SliME, VITA series (Vita, Vita 1.5), Long Vita, Kwai Keye-VL, Kwai Keye-VL 1.5, and Thyme: Think Beyond Images. Published multiple papers, including MME-Realworld (ICLR 2025), ErrorRadar (ICLR 2025 Workshop), MME-Unify, MME-VideoOCR, MM-RLHF (ICML 2025), and DAMO (ICML 2025). Received the AAAI 2025 AI Innovation in Application Award.
Research Experience
Worked with Prof. Jingdong Wang at Microsoft Research Asia and Prof. Rong Jin at Alibaba DAMO Academy. Primary research focuses on the training, evaluation, and post-training techniques for multimodal models.
Education
Ph.D. candidate at the University of Chinese Academy of Sciences, State Key Laboratory of Pattern Recognition; Advisor: Prof. Tieniu Tan. Formerly interned at Microsoft Research Asia and Alibaba DAMO Academy.
Background
A fourth-year Ph.D. student at the State Key Laboratory of Pattern Recognition, University of Chinese Academy of Sciences, with a focus on the training and evaluation of multimodal large-scale models, particularly in developing efficient alignment strategies and comprehensive evaluation frameworks for vision-language systems.
Miscellany
Actively seeking research positions in both industry and academia, with a strong belief in the power of interdisciplinary collaboration and its potential for driving impactful research outcomes.