• Jump to Content
北京大学计算机研究所多媒体信息处理研究室
[中文版] [English Version]
Document Title
主页
新闻
成员
招生方向
研究方向 招生要求 毕业生简介
科研项目
主要论文
开设课程
国际评测
发明专利
学生荣誉
活动休闲



Geng   Li  [中文版]



Ph.D. Candidate (Supervisor: Prof. Yuxin Peng)

Multimedia Information Processing Lab

Wangxuan Institute of Computer Technology

Peking University

No. 128, Zhong-Guan-Cun North Street

Beijing 100080, China

E-mail: ligeng@stu.hit.edu.cn
















Research Directions

  • Fine-grained Visual Reasoning

Education

  • Ph.D. Candidate, Computer Science and Technology (Intelligence Science and Technology), Wangxuan Institute of Computer Technology, Peking University, 2023 - Now
  • Master of science: Computer Science and Technology, Faculty of Computing, Harbin Institute of Technology 2021-2023
  • Bachelor of science: Computer Science and Technology, Faculty of Computing, Harbin Institute of Technology 2017-2021

Awards

  • 2022              National Scholarship
  • 2022              Excellent Student Cadre, HIT
  • 2022              School Outstanding Student/Dean’s List, HIT
  • 2021              Top Ten Outstanding Graduates of Honors School, HIT
  • 2021              Outstanding Graduates of University, HIT
  • 2017-2021     National Encouragement Scholarship, The First Prize of the people's scholarship in China

Publication

  1. Yuxin Peng*, Zishuo Wang, Geng Li, Xiangtian Zheng, Sibo Yin and Hulingxiao He, "A Survey on Fine-Grained Multimodal Large Language Models", Chinese Journal of Electronics (CJE), 2026. (Accept)【pdf】
  2. Geng Li, Jinglin Xu, Yunzhen Zhao and Yuxin Peng*, "DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding", 38th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Music City Center, Nashville TN, USA, Jun. 11-15, 2025. (Highlight, 13.5%) 【pdf】【source code】【Poster】【VALSE 报道】【CVer报道】【极市平台报道】
  3. Hulingxiao He, Geng Li, Zijun Geng, Jinglin Xu and Yuxin Peng*, "Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models", The Thirteenth International Conference on Learning Representations (ICLR), Singapore, Apr. 24-28, 2025. 【pdf】【source code】【model】【CSIG报道】【机器之心报道】【Poster】【Slides】
  4. Geng Li, Boyuan Ren and Hongzhi Wang, "EEML: Ensemble Embedded Meta-Learning.", International Conference on Web Information Systems Engineering (WISE), pp. 433-442, Biarritz, France, Nov. 1–3, 2022.

Personal Interests

  • Badminton

北京大学王选计算机研究所多媒体信息处理研究室