Published several papers, including a paper on evaluating the prompt steerability of LLMs accepted to the pluralistic alignment workshop at NeurIPS 2024, and an attack atlas paper accepted to the red teaming GenAI workshop at NeurIPS 2024. Also served as a program committee member for multiple academic conferences.
Research Experience
Currently a Research Scientist in the trustworthy AI group at IBM Research. Previously, a postdoctoral research associate at the Coordinated Science Lab, University of Illinois at Urbana–Champaign, focusing on reinforcement learning, control, and games.
Education
Ph.D. in Electrical Engineering and Computer Science from the University of Michigan, under the supervision of Demos Teneketzis; Postdoctoral Research Associate at the Coordinated Science Lab, University of Illinois at Urbana–Champaign, working with Tamer Başar and Cedric Langbort.
Background
Primary research interests include multi-agent coordination and alignment, fairness of learning algorithms in sequential decision environments, and human-AI interaction (e.g., via language models). Currently a research scientist at IBM Research.