Lin Li

PhD student @ KCL, Incoming Postdoc @ OATML, Oxford

prof_pic.jpg

I am a PhD student supervised by Prof. Michael Spratling in the Department of Informatics at King’s College London. I received a MSc degree in computing with my thesis advised by Prof. Wayne Luk from Imperial College London. I also received a B.M. in finance with my thesis advised by Prof. Zheng Qiao from Xiamen University.

My research interests include

  • Hallucination in (multimodal) LLMs
  • LLM Jailbreaking, Safety Alignment, and Adversarial ML
  • AI Society and LLM Agent
  • AI+ Applications: healthcare, robotics, business

news

Mar 1, 2025 A new co-authored article, titled “Reducing Large Language Model Safety Risks in Women’s Health using Semantic Entropy”, is available at arXiv now.
Feb 17, 2025 Invited to review for ICML 2025 and NeurIPS 2025.
Feb 15, 2025 My first-authored work, Robust shortcut and disordered robustness: Improving adversarial training through adaptive smoothing, is online now at the Pattern Recognition (PR).
Feb 9, 2025 Serve as the Program Committee of the 2nd MEIS Workshop @CVPR2025.
Feb 9, 2025 Invited to review for the journals IEEE T-PAMI, IEEE T-IFS, IEEE T-DSC, and Pattern Recognition.

selected publications

  1. AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation
    Lin Li, Jianing Qiu, and Michael Spratling
    International Journal of Computer Vision, 2024
    PDF
  2. One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
    Lin Li*, Haoyan Guan*, Jianing Qiu, and 1 more author
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    PDF
  3. OODRobustBench: a benchmark and large-scale analysis of adversarial robustness under distribution shift
    Lin Li, Yifei Wang, Chawin Sitawarin, and 1 more author
    In International Conference on Machine Learning (ICML) and ICLRW-DMLR, 2024
    PDF
  4. Advancing Robots with Greater Dynamic Dexterity: A Large-Scale Multi-View and Multi-Modal Dataset of Human-Human Throw&Catch of Arbitrary Objects
    Lipeng Chen*, Jianing Qiu*, Lin Li*, and 3 more authors
    International Journal of Robotics Research (IJRR), 2024
    PDF
  5. Data Augmentation Alone Can Improve Adversarial Training
    Lin Li, and Michael Spratling
    In International Conference on Learning Representations (ICLR), 2023
    PDF
  6. Large AI Models in Health Informatics: Applications, Challenges, and the Future
    Jianing Qiu, Lin Li, Jiankai Sun, and 10 more authors
    IEEE Journal of Biomedical and Health Informatics (JBHI), 2023
    PDF