An Yu

I'm a third-year PhD student

I am a Ph.D. student in Computer Science at the University at Albany, SUNY, working in the Computer Vision and Machine Learning (CVML) Laboratory under the supervision of Prof. Ming-Ching Chang.

I work on multimodal AI, focusing on video understanding, temporal reasoning, and multimodal large language models. My research spans model development, efficiency, and benchmarking, with applications in both general video understanding and biomedical analysis.

news

Jun 24, 2026	I’m excited to share that our Paper “RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization” has been accepted to MICCAI 2026!
May 26, 2026	I’m excited to share that our Paper “SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM” has been accepted to IEEE TMM Journal!
May 01, 2026	I’m excited to share that our Paper “FlashSinkhorn: IO-Aware Entropic Optimal Transport” has been accepted to ICML 2026 as a Spotlight(Oral Presentation) Paper!
Apr 14, 2026	I’m excited to share that our Paper “Llava-mr: Large language-and-vision assistant for video moment retrieval” has been accepted to ICPR 2026!
Apr 14, 2026	I’m excited to share that our Paper “FAVE: A Structured Benchmark for Fine-Grained Audio-Visual Temporal Evaluation in Multimodal LLMs” has been accepted to CVPR 2026!