J.D. Zamfirescu-Pereira

ASSISTANT PROFESSOR
COMPUTER SCIENCE

Engineering VI - Room 484

Email: zamfi@cs.ucla.edu
Phone: (310) 206-9115

Websites

Joint Human & AI Systems

Paper & Talk: "Beyond Code Generation: LLM-supported Exploration of the Program Design Space", J.D. Zamfirescu-Pereira, E. Jun, M. Terry, Q. Yang, B. Hartmann; In CHI ‘25, Yokohama, Japan. Recipient of a "Best
Paper Honorable Mention" Award
Paper & Talk: "61A-Bot Report: AI Assistants in CS1 Save Students Homework Time and Reduce Demands on Staff. (Now What?)", J.D. Zamfirescu-Pereira, L. Qi, B. Hartmann, J. DeNero, N. Norouzi; In SIGCSE ‘25, Pittsburgh, PA
Paper: "Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences", S. Shankar, J.D. Zamfirescu-Pereira, B. Hartmann, A. Parameswaran, I. Arawjo; In UIST ‘24, Pittsburgh, PA
Invited Talk & Panel: Is “Good Enough” Good Enough? Considerations for Deploying LLMbased Systems, on a panel for AI “Deployment Safeguards”, 8th Annual CHAI Workshop (Berkeley Center for Human-Compatible AI), Asilomar, CA.
Paper & Talk: "Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts", J.D. Zamfirescu-Pereira, R. Wong, B. Hartmann, Q. Yang; In CHI '23, Hamburg, Germany.
Invited Podcast: Why Prompting is Hard, with J.D. Zamfirescu-Pereira