Tianyang Zhou

PhD Student (2023 - Present)
Tianyang is a Ph.D. student focusing on program language translation and software security, with an emphasis on machine learning for code. Currently he is working on developing techniques for verified C-to-Rust translation and analyze security implications of AI-geneingrated code.
Personal Website | Google Scholar | GitHub | Email

Qilong Wu

PhD Student (2023 - Present)
Qilong is a Ph.D. student in Computer Science at UIUC, advised by Prof. Varun Chandrasekaran. Qilong earned an M.S. in Computer Science at UIUC and a B.S. from Nanjing University (Kuang Yaming Honors School). Qilong also served as a research assistant at the Berkeley AI Research (BAIR) Lab in 2021. His work focuses on trustworthy machine learning, including multitask and transfer learning, as well as security aspects in machine learning.
Personal Website | Google Scholar | GitHub | Email

Yian Wang

PhD Student (2023 - Present)
Yian Wang is a PhD student in Computer Science at UIUC. Her research focuses on trustworthy AI, including machine unlearning, foundation model safety, and privacy and safety in multi-agent AI systems. Her work explores how to make AI models and agent systems more reliable, controllable, and trustworthy.
Personal Website | Google Scholar | GitHub | Email

Pragati Meshram

PhD Student (2024 - Present)
Pragati is a PhD student in Electrical and Computer Engineering at UIUC. She received her Bachelor's and Master's degrees from IIT Bombay, India. Her research spans multimodal learning, vision-language models (VLMs), and generative AI security. She is particularly interested in building reliable and interpretable multimodal systems and understanding their limitations.
Personal Website | Google Scholar | GitHub | Email

Yiwei Fu

PhD Student (2025 - Present)
Yiwei Fu is a Ph.D. student in the Computer Science at UIUC. His main research interest is in privacy, safety, and alignment of machine learning systems. Previously, he worked at Grainger as a applied machine learning scientist, and earned a MS degree at Carnegie Mellon University and BS degree at University of Michigan.
Personal Website | Google Scholar | Email

Yi (Evie) Zhang

PhD Student (2025 - Present)
Yi (Evie) Zhang is a Ph.D. student in Computer Science at UIUC and an Amazon AI PhD Fellow. Her research focuses on Human-Centered AI and AI Safety. She is interested in the broader social impacts of AI, as well as exploring the technical solutions and policies needed to address them. She earned her B.A. from Renmin University of China and her M.S. from UC Irvine.
Personal Website | Google Scholar | Email

Vira Kasprova

PhD Student (2025 - Present)
Vira is a Ph.D. student in Computer Science at UIUC. She received her Bachelor's degree in Computer Science from UIUC in 2025. Her research spans AI safety, LLM agents, and trustworthy machine learning. She is particularly interested in AI oversight, alignment, and sycophancy in multi-agent systems.
Personal Website | Google Scholar | Email

Xiangwen Wang

Master's Student (2025 - Present)
Xiangwen is a Master's student in Computer Science at UIUC. She received her Bachelor's degree from the University of Science and Technology of China (USTC). Her research focuses on post-training of large language models and trustworthy machine learning, with a particular emphasis on alignment and emerging risks in advanced LLMs.
Personal Website | Google Scholar | GitHub | Email

Shengxin (Jack) Zhang

Master's Student (2026 - Present)
Jack is a Master's student in Electrical and Computer Engineering at UIUC. His research explores diversity in AI-generated peer review, fairness under distribution shift, and robust representations. He combines statistical thinking with hands-on engineering to understand how intelligent systems behave and how to improve them.
Personal Website | Google Scholar | Email