Published a paper on a Multi-Grained Teaching Strategy for Efficient Text-to-Video Retrieval at CVPR 2024; published two papers at ICCV 2025, one on Music Grounding by Short Video (first author) and another on Sketch Animation; published a paper on Ad-hoc Video Search at ACMMM 2025; published a paper on Text-based Person Search at ICME 2025.
Research Experience
Interned at Tencent and Kuaishou, working on video understanding and video-music retrieval.
Education
Graduated from Sichuan University's Top-notch Program (a class of 15 elite students selected from 400+) in 2024, supervised by Prof. Qijun Zhao; currently a second-year Ph.D. student at the AI & Media Computing Lab, Renmin University of China, advised by Prof. Xirong Li.
Background
Research interests include multi-media learning, video understanding, cross-modal retrieval, and open-set recognition, complemented by a broad curiosity in generative models, RAG, RL, and LLM.