Papers accepted by NeurIPS, ICML, CVPR, T-PAMI, ECCV, ICLR, and Pattern Recognition; awarded the Baidu Scholarship (one of 10 Ph.D. students worldwide), China National Scholarship for Ph.D. students (highest student honor in China), and Outstanding Graduate of Sichuan province; published a survey on audio-visual learning.
Research Experience
Visited the Human Sensing Lab at CMU; attended the VALSE 2025 student workshop; gave talks about balanced multimodal learning at Virginia Tech and TechBeat; released MokA, a new PEFT pipeline for MLLMs, ensuring both unimodal and cross-modal adaptation.
Education
Ph.D. student at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Di Hu; Bachelor's degree in Computer Science and Technology from the University of Electronic Science and Technology of China (UESTC) from 2017 to 2021.
Background
Research interests focus on multimodal learning, including multimodal learning mechanisms and MLLMs.
Miscellany
Has a WeChat discussion group about balanced multimodal learning.