Li Zhang

I am a Ph.D. candidate in the Department of Electrical and Computer Engineering at UC San Diego, working on machine learning under the supervision of Prof. Pengtao Xie. Previously, I received my Master’s degree from Zhejiang University.

My research has primarily focused on computer vision, deep learning, and large language/vision models (foundation models). In my prior work, I developed multi-level frameworks to train more powerful models, trained large foundation models in distributed environments, and fine-tuned visual foundation models (SAM) for task-specific applications. A more detailed overview of my work is available in my CV.

News

  • [07/2025] I co-organize a NeurIPS 2025 workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences.
  • [07/2025] ProteinAligner is accepted to ICML 2025 Workshop.
  • [07/2025] GenSeg is accepted to Nature Communications.
  • [01/2025] Extension of LFM is accepted to IEEE Transactions on Artificial Intelligence.
  • [05/2024] BLO-SAM is accepted to ICML 2024.
  • [12/2021] LFM is accepted to AAAI 2022.

Selected Publications

(* denotes co-first authors)

  • Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes.

    Li Zhang, Basu Jindal, Ahmed Alaa, Robert Weinreb, David Wilson, Eran Segal, James Zou, Pengtao Xie

    Nature Communications, 2025

    PDF CODE

  • BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation

    Li Zhang, Youwei Liang, Ruiyi Zhang, Amirhosein Javadi, Pengtao Xie

    International Conference on Machine Learning (ICML), 2024

    PDF CODE

  • Learning from Mistakes – a Framework for Neural Architecture Search

    Bhanu Garg, Li Zhang, Pradyumna Sridhara, Ramtin Hosseini, Eric Xing, Pengtao Xie

    Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022

    PDF CODE

  • An integrated bottom-up approach for leak detection in water distribution networks based on assessing parameters of water balance model

    Jie Yu, Li Zhang, Jinyu Chen, Yao Xiao, Dibo Hou, Pingjie Huang, Guangxin Zhang, Hongjian Zhang

    Water, 2021

    PDF

More Publications

Professional Activities

  • [06/2025 - Now] Research Scientist Intern at Adobe, San Jose.
    • Watermark-Based Concept Attribution via Prompt Inversion​
  • [06/2023 - 09/2023] Research Assistant at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).
    • TProtein foundation model pre-train and applications.

Teaching Activities

  • [03/2025 - 06/2025] Teaching Assistant for ECE285 Deep Generative Model at UCSD.