Lin Li
PhD student @ KCL, Incoming Postdoc @ OATML, Oxford
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
- Jailbreaking and safety alignment
- Adversarial machine learning
- LLM Agent
- AI+ Applications: healthcare, robotics, business
news
| Sep 24, 2024 | My first-authored (equal contribution) work, Advancing robots with greater dynamic dexterity: A large-scale multi-view and multi-modal dataset of human-human throw&catch of arbitrary objects, is online now at the International Journal of Robotics Research (IJRR). |
|---|---|
| Aug 24, 2024 | A first-authored work, AROID: Improving Adversarial Robustness through Online Instance-wise Data Augmentation, is accepted by the International Journal of Computer Vision (IJCV). |
| Jul 20, 2024 | Invited to serve as Program Committee for AAAI 2025. What a fancy name of reviewer! |
| Jun 7, 2024 | A first-authored work, Advancing Robots with Greater Dynamic Dexterity: A Large-Scale Multi-View and Multi-Modal Dataset of Human-Human Throw&Catch of Arbitrary Objects, is accepted by the International Journal of Robotics Research (IJRR). |
| May 2, 2024 | Our work, OODRobustBench: a benchmark and large-scale analysis of adversarial robustness under distribution shift, is accepted by ICML 2024. Be careful! your adversarially robust model is probably much less robust under distribution shifts. |
selected publications
-
AROID: Improving Adversarial Robustness Through Online Instance-Wise Data AugmentationInternational Journal of Computer Vision, 2024 -
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language ModelsIn IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 -
OODRobustBench: a benchmark and large-scale analysis of adversarial robustness under distribution shiftIn International Conference on Machine Learning (ICML) and ICLRW-DMLR, 2024 -
Advancing Robots with Greater Dynamic Dexterity: A Large-Scale Multi-View and Multi-Modal Dataset of Human-Human Throw&Catch of Arbitrary ObjectsInternational Journal of Robotics Research (IJRR), 2024 -
Data Augmentation Alone Can Improve Adversarial TrainingIn International Conference on Learning Representations (ICLR), 2023 -
Large AI Models in Health Informatics: Applications, Challenges, and the FutureIEEE Journal of Biomedical and Health Informatics (JBHI), 2023