Publications

* indicates equal contribution; † indicates the corresponding author if have. A latest list of publications can be found at Google scholar.

2025

  1. Robust Shortcut and Disordered Robustness: Improving Adversarial Training Through Adaptive Smoothing
    Lin Li†, and Michael Spratling
    Pattern Recognition (PR), 2025
  2. Reducing Large Language Model Safety Risks in Women’s Health using Semantic Entropy
    Jahan C Penny-Dimri, Magdalena Bachmann, William R Cooke, Sam Mathewlynn, Samuel Dockree, John Tolladay, Jannik Kossen, Lin Li, Yarin Gal, and Gabriel Davis Jones
    The Lancet Obstetrics, Gynaecology, & Women’s Health, 2025
  3. Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
    Ravi Shankar, Sheng Wong, Lin Li, Magdalena Bachmann, Alex Silverthorne, Beth Albert, and Gabriel Davis Jones
    NeurIPS Workshop GenAI4Health, 2025
  4. Building Reliable Long-Form Generation via Step-Wise Hallucination Rejection Sampling
    Lin Li, Georgia Channing, Suhaas M Bhat, Gabriel Davis Jones, and Yarin Gal
    in submission, 2025
  5. Towards Robust Protective Perturbation against DeepFake Face Swapping
    Hengyang Yao*, Lin Li*, Ke Sun, Jianing Qiu, and Huiping Chen
    in submission, 2025
  6. Emerging Cyber Attack Risks of Medical AI Agents
    Jianing Qiu, Lin Li, Jiankai Sun, Hao Wei, Zhe Xu, Kyle Lam, and Wu Yuan
    in submission, 2025

2024

  1. AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation
    Lin Li†, Jianing Qiu, and Michael Spratling
    International Journal of Computer Vision (IJCV), 2024
  2. One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
    Lin Li*, Haoyan Guan*, Jianing Qiu, and Michael Spratling
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
  3. OODRobustBench: a benchmark and large-scale analysis of adversarial robustness under distribution shift
    Lin Li, Yifei Wang, Chawin Sitawarin, and Michael Spratling
    International Conference on Machine Learning (ICML) and ICLRW-DMLR, 2024
    Benchmark
  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*, Xi Luo, Guoyi Chi, and Yu Zheng
    International Journal of Robotics Research (IJRR), 2024
    Web
  5. Development and Validation of a Multimodal Multitask Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence
    Jianing Qiu*, Jian Wu*, Hao Wei*, Peilun Shi, Minqing Zhang, Yunyun Sun, Lin Li, Hanruo Liu, Hongyi Liu, Simeng Hou, and 32 more authors
    New England Journal of Medicine - Artificial Intelligence (NEJM AI), 2024
  6. Artificial Intelligence for Biomedical Video Generation
    Linyuan Li, Jianing Qiu, Anujit Saha, Lin Li, Poyuan Li, Mengxian He, Ziyu Guo, and Wu Yuan
    arXiv, 2024

2023

  1. Data Augmentation Alone Can Improve Adversarial Training
    Lin Li, and Michael Spratling
    International Conference on Learning Representations (ICLR), 2023
  2. Understanding and combating robust overfitting via input loss landscape analysis and regularization
    Lin Li, and Michael Spratling†
    Pattern Recognition (PR), 2023
  3. Large AI Models in Health Informatics: Applications, Challenges, and the Future
    Jianing Qiu, Lin Li, Jiankai Sun, Jiachuan Peng, Peilun Shi, Ruiyang Zhang, Yinzhao Dong, Kyle Lam, Frank P.-W. Lo, Bo Xiao, and 3 more authors
    IEEE Journal of Biomedical and Health Informatics (J-BHI), 2023