About Me

I am a first-year Master’s student in Computer Science at the University of Illinois at Urbana-Champaign (UIUC), advised by Prof. Bo Li in the Secure Learning Lab.

Previously, I received my Bachelor’s degree in Computer Engineering from Shanghai Jiao Tong University.

My research focuses on multimodal large language models, AI safety, and AI agents. I am particularly interested in developing safe, efficient, and practical multimodal agents that can effectively interact with and understand the world through multiple modalities.

My research aims to build capable, safe, and trustworthy AI agents that learn from both observations and knowledge. I explore this through two pathways: (1) strengthening their internal intelligence and alignment by bootstrapping from experience and hindsight, and (2) applying external constraints grounded in human knowledge to achieve compliance and certifiability.

The long-term goal of my research is to contribute to the development of AI systems that are not only powerful but also reliable, interpretable, and aligned with human values, particularly in multimodal settings where agents must process and reason about diverse types of information.

Research Interests:

• Multimodal Large Language Models
• AI Safety and Alignment
• AI Agents and Reasoning
• Trustworthy Machine Learning
• Robust AI Systems

Contact:

• Email: haibot2@illinois.edu
• GitHub: EchoRaven
• Google Scholar: Haibo Tong