news

Sep 28, 2026 I started MATS with SaferAI.
Aug 31, 2026 I attended the IPAM Foundations of Interpretability Workshop and presented PLOT.
Jul 06, 2026 I attended ICML 2026 in Seoul, South Korea and presented at the workshops for Pluralistic Alignment and Mechanistic Interpretability.
Apr 23, 2026 I attended ICLR 2026 in Rio de Janeiro, Brazil and gave an oral presentation.
Apr 01, 2026 With my SPAR team, we released ValueArena, a leaderboard for value alignment.
Jan 26, 2026 “EigenBench: A Comparative Behavioral Measure of Value Alignment” was accepted to ICLR 2026 for an Oral presentation.
May 21, 2025 I was selected as a Siegel PiTech PhD Impact Fellow to work with NYC DEP for Summer 2025.