Published over 10 papers in IEEE Trans. and CCF A-class journals such as TIP, TMM, IJCAI, AAAI, and ACM MM.
Selected for the 2025 Beijing 'High-level Innovation Plan' Young Talent Support Program.
Received the 2024 Beijing Image and Graphics Society (BSIG) Excellent Doctoral Dissertation Award.
The multimodal large model TeleMM ranked third in the 2024 OpenCompass overall list, surpassing GPT-4o.
Won first place in the TRECVID Video Example Search Competition in 2019 and 2020.
Third prize in the BOE Innovation Challenge National Finals, Special Offer from BOE Maker Lab.
Background
Research Interests: Multimodal Large Models, Multimodal Content Understanding, Fine-grained Visual Analysis. Currently a Visual Algorithm Engineer at China Telecom Artificial Intelligence Institute.