Yiming Zhang

| Email | Github |

I am a second-year student within the Joint Ph.D Programme of Intelligent Institute of Machine at Hefei Institute of Physical Science,Chinese Academy of Science and University of Science and Technology of China advised by Prof. Yining Sun and Prof. Zenghui Ding. Previously, I received my Master degree in Data Science and Analytics at Hong Kong Polytechnic University.

My research interests center on trustworthy deployment with large foundation models (e.g. LLMs, LVLMs) from both a theoretical and empirical perspective. My recent work focus on efficient multimodal fusion in language models (e.g., images-text, videos-text) while improving their fairness, reducing hallucinations, and strengthening their reasoning capabilities.

Email: yimingzhang@mail.ustc.edu.cn


News

  • [June., 2025] 🌟 Two first-authored papers accepted by ICCV 2025.
  • [May., 2025] 🌟 One paper accepted by ACL 2025.

  Publications
sym

CircuitProbe: Dissecting Spatiotemporal Visual Semantics with Circuit Tracing
Yiming Zhang*, Chengzhang Yu*, Zhuokai Zhao*, Kun Wang, Qiankun Li, Zihan Chen, Yang Liu, Zenghui Ding, Yining Sun
Arxiv

sym

FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights
Chengzhang Yu*,Yiming Zhang*, Zhixin Liu, Zenghui Ding, Yining Sun and Zhanpeng Jin
Accepted to ACL 2025

sym

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen, Zenghui Ding, Xianjun Yang and Yining Sun
Accepted to ICCV 2025

sym

RankCLIP: Ranking-Consistent Language-Image Pretraining
Yiming Zhang*, Zhuokai Zhao*, Zhaorun Chen, Zhili Feng, Zenghui Ding and Yining Sun
Accepted to ICCV 2025