About me

I am a first-year Computer Science Ph.D. student at Texas A&M University, advised by Prof. Kuan-Hao Huang. Broadly, my research is in AI safety and interpretability: I study how large language models represent and process information internally, and use those insights to make them more reliable and controllable, from reducing sycophancy and hallucination to steering how models handle different languages.

Before my Ph.D., I completed my M.S. at UIUC with Prof. Hao Peng and Prof. Dilek Hakkani-Tür, and worked as an AI/ML Research Engineer at MathGPT.ai. Outside research, you can find me lifting at the gym or hunting down the best food spots in town.

I’m always happy to chat about research. Feel free to reach out via email or see my CV.

  • FLAIR Lab, Texas A&M University
    Ph.D. Student Researcher
    Sycophancy mitigation, multilingual steering, VLM hallucination detection
  • MathGPT.ai
    AI/ML Research Engineer
    Built MathRobust-LV, a robustness benchmark for LLM math reasoning
  • University of Illinois Urbana-Champaign
    Graduate Student Researcher, Alta Lab & ConvAI Lab
    Hallucination detection from hidden states; persuasion-based jailbreaks
  • University of Illinois Urbana-Champaign
    Teaching Assistant, CS 105
    Outstanding Teaching Assistant Award (Spring 2024)
  • RBCDSAI, IIT Madras
    Post-Baccalaureate Fellow
    Hidden Voices (Wikipedia biographies of women in STEM); graph learning

Click here for publications →