Hi there! ▮

Geng Li (李耕)

avatar

I am a second-year Ph.D. student at the Wangxuan Institute of Computer Technology, Peking University (PKU), advised by Prof. Yuxin Peng. My research focuses on Multimodal Large Language Models (MLLMs/LMMs), with a particular interest in fine-grained perception (CVPR 2025 Highlight / ICLR 2025). I am also broadly interested in multimodal reasoning, LLM-based tool use, and embodied agents. Prior to joining PKU, I received both my Bachelor’s and Master’s degrees from Harbin Institute of Technology (HIT), where I worked with Prof. Hongzhi Wang on AutoML/Meta-learning. In the fall of 2020, I join a semester exchange program at Johns Hopkins University (JHU, at Maryland), thanks to the Honor School of HIT.

Beyond research, I enjoy playing badminton and exploring the I Ching (周易).

Latest Publications

  [CVPR 2025 (Highlight)]  DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding

  [ICLR 2025]  Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models

  [TKDE 2023]  Automated Graph Neural Network Search Under Federated Learning Framework

  [WISE 2022]  EEML: Ensemble Embedded Meta-Learning