Qin Liu - Team leader
Qin Liu is a third-year CS PhD student at UC Davis. Her research focuses on reliable, controllable, and trustworthy LLM with a particular emphasis on model robustness and safety, including adversarial robustness and backdoor attack /defense. She has also extended her research on safety alignment to multi-modal models.
Wenjie Mo - Co-team leader
Jacky Mo is a first-year CS PhD student at UC Davis. He primarily focuses on AI safety, particularly in building secure and reliable LLMs and LLM4Code. He explores various aspects of safety and robustness of these models, including defending against and detecting backdoor attacks. In addition, his work extends to understanding and mitigating jailbreak attacks, where models are manipulated to generate harmful or unintended outputs
Xiaofei Wen
Xiaofei is a first-year computer science PhD student at UC Davis. His research interest lies in Natural Language Processing and interactive Dialogue Systems. Currently, he is focused on Red Teaming Language Models, with a particular emphasis on evaluating and enhancing LLMs’ robustness in dialogue tasks. His work aims to identify vulnerabilities and improve the safety and reliability of AI-driven interaction.
Dongwon Jung
Dongwon Jung is a first-year Ph.D. student in Computer Science at UC Davis. His research interest lies in Natural Language Processing and Information Retrieval, with a particular focus on Retrieval-Augmented Generation (RAG) and LLM-based agents. He is currently working on effectively combining LLM’s internal knowledge with retrieved knowledge to tackle knowledge-intensive tasks.
Hadi Askari
Hadi is a fourth-year PhD student at UC Davis. Hadi has worked in analyzing robustness and bias in large language models for end tasks like summarization, recommendations, and using ML techniques to do social good (i.e. increase news consumption). He is currently working on projects to improve demonstration selection for in-context learning for Indirect in-context learning.
Bangzheng Li
Bangzheng Li is a third-year PhD student in computer science at LUKA lab, UC Davis. His research interest lies in the reasoning trajectories of AI systems across different modalities. His approaches introduce human cognitive processes into computational models, and he has 12 publications in top-tier NLP and CV conferences.
Terry Tong
Terry Tong is a third-year undergraduate studying Computer Science and Engineering as well as General Statistics at UC Davis. He focuses on leveraging robust machine learning for natural language processing. He is supported by the UC Davis Provost's Fellowship and HK Scholarship which has led to a first-author paper at EMNLP-findings.
Muhao Chen - Faculty Advisor
Muhao Chen is an Assistant Professor at the Department of Computer Science, UC Davis, where he leads the Language Understanding and Knowledge Acquisition (LUKA) Group. His research focuses on robust and accountable ML. Most recently, his group has been focusing on accountability and security problems of large language models and multi-modal language models.
