February 2024: Starting remote internship at Microsoft GenAI team
February 2023: One paper accepted for CVPR 2023
November 2022: One paper accepted for CVIU
July 2022: One paper accepted for ECCV 2022
June 2022: Presenting ECLIPSE at CVPR 2022 Sight and Sound workshop
November 2021: Presenting NeurIPS paper at NeurIPS Taipei Meetup
September 2021: One paper accepted for NeurIPS 2021; Serving as a program committee for AAAI 2022
June 2021: Presenting Unsupervised Sound Localization via Iterative Contrastive Learning at CVPR 2021 Sight and Sound workshop
December 2020: One paper accepted for AAAI 2021
September 2020: One paper accepted for ACCV 2020
November 2019: Master Thesis Honorable Mention Award by TAAI
August 2019: Master Thesis Honorable Mention Award by IPPR
July 2019: One paper accepted for ICCV 2019
February 2019: One paper accepted for ICASSP 2019
Background
Currently a Ph.D. student in the Department of Computer Science at UNC Chapel Hill, working with Prof. Gedas Bertasius. Research interests lie in Deep Learning and Computer Vision, particularly multimodal learning with multi-modality data.
Miscellany
Currently on the job market, seeking research scientist or engineer roles. Focuses on efficient audio/video understanding, including pretraining, model adaptation, and reasoning with LLMs. Also works on multimodal generation and editing. Interned at ByteDance, Microsoft, and Adobe Research.