I am a third-year Ph.D. Candidate in Computer Science and Engineering at the University of California, Santa Cruz, advised by Yang Liu. My research currently focuses on LLM alignment and safety, LLM Reasoning, and responsible LLM agents. I also work on LLM unlearning. I study how to adapt and control LLMs to ensure safe, robust, and reliable behavior. My long-term goal is to develop safe, robust, generalizable, and trustworthy LLM-based systems. I have been working as a Research Scientist Intern focusing on conducting high impact research in the Generative AI space at Accenture Data & AI Research Center since June 2024.

More about my research interests:
• LLM Alignment, Unlearning, Reasoning, and Post-training
• LLM Agents: Safe, scalable, and trustworthy LLM-based agentic systems
• Trustworthy Machine Learning: Fairness, Interpretability, Robustness
• Representation Learning & Learning from Dynamic and Noisy Data

I am interested in building intelligent agents or models that can learn from various data sources (e.g., images, audio, and text) and automate decision-making processes in uncertain environments to solve multiple real-world tasks realiably and efficiently. I love the process of giving machines the intelligence to address real-world problems.