LMOD Dataset and Benchmark
This study proposes a systematic data and evaluation pipeline that repurposes existing datasets to curate a dataset for the development and evaluation of largevision-language models in ophthalmology.
Read More
I was honored to serve as an Area Chair for ARR Oct 2025. I am humbly happy to make contributions to the ACL community.
I was honored to give an invited lecture at Sino-American Pharmaceutical Professionals Association (SAPA) on generative AI in healthcare.
Our paper on geometry problem solving with large vision-language models has been accepted by EMNLP Findings 2025. I'm grateful to have collaborated with an amazing team: Seunghyuk, Yang, Youngbin, Seungbeom, and Dongwoo.
LMOD was invited to present at AMIA 2025 as a podium abstract. I'm grateful to have collaborated with an amazing team: Yu, Dylan, Xuansheng, Ke, Yih-Chung, Ninghao, Xiuzhen, and Qingyu.
I was honored to give a talk at Envisioning AI at Yale on the topic of AI in healthcare. It was wonderful to meet and learn from so many talented researchers.
I was honored to present our work on LMOD at NAACL 2025. It was wonderful to meet and learn from so many talented researchers.
I was honored to present our work on HandCraft at WACV 2025. It was wonderful to meet and learn from so many talented researchers.
Our paper on multimodal large models and ophthalmology benchmarks has been accepted by NAACL Findings 2025. I'm grateful to have collaborated with an amazing team: Yu, Dylan, Xuansheng, Ke, Yih-Chung, Ninghao, Xiuzhen, and Qingyu.
I was honored to become an Associate PhD Supervisor at the Australian National University (ANU). I look forward to supporting students as they grow and achieve their research goals.
I was honored to serve as an Area Chair for NAACL 2025. I am humbly happy to make contributions to the ACL community.
I was honored to present our work on Set-of-Vision Prompting at EMNLP 2024. It was wonderful to meet and learn from so many talented researchers.
Our paper on diffusion models and generative models has been accepted by WACV 2025. I'm grateful to have collaborated with an amazing team: Yiqun, Yang, and Dylan.