I am a current research intern and incoming MSc Computer Vision student at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), advised by Prof. Yutong Xie. Before that, I graduated from the University of Science and Technology of China (USTC) with a B.E. in Computer Science.
My research interests include computer vision, multimodal language models, and multimodal agents, especially in the context of AI for healthcare. I’m actively looking for collaboration and PhD opportunities, please feel free to drop me an email if interested.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Mohamed bin Zayed University of Artificial IntelligenceM.Sc. in Computer VisionAug. 2026 - present -
University of Science and Technology of ChinaB.E. in Computer ScienceSep. 2021 - Jul. 2025
Honors & Awards
-
Outstanding, National Innovation Program2025
-
Bronze Academic Scholarship2022
-
Class of Honors Scholarship2021, 2022
-
Multiple Provincial and University Swimming Records
Experience
-
Mohamed bin Zayed University of Artificial IntelligenceResearch InternNov. 2025 - Now
-
Stony Brook UniversityResearch InternDec. 2024 - Jun. 2025 -
iFLYTEKSoftware Engineer InternJul. 2024 - Oct. 2024
News
Selected Publications (view all )
MemSurg: Memory-Augmented Long-Horizon Reasoning for Surgical Video Understanding
Anonymous Authors
Submitted to MICCAI 2026
MemSurg is a memory-augmented framework for long-horizon surgical video understanding that leverages guided prompting and chain-of-thought reasoning. By constructing an external surgical memory graph from segmentation and motion cues, it retrieves task-relevant evidence across time and composes more coherent prompts for downstream inference. This design improves consistency on instrument, action, and workflow understanding, outperforming GPT-4o and by 22.42%.
MemSurg: Memory-Augmented Long-Horizon Reasoning for Surgical Video Understanding
Anonymous Authors
Submitted to MICCAI 2026
MemSurg is a memory-augmented framework for long-horizon surgical video understanding that leverages guided prompting and chain-of-thought reasoning. By constructing an external surgical memory graph from segmentation and motion cues, it retrieves task-relevant evidence across time and composes more coherent prompts for downstream inference. This design improves consistency on instrument, action, and workflow understanding, outperforming GPT-4o and by 22.42%.