Research Leadership and Trustworthy AI

I also lead collaborative research projects beyond my primary research programs, helping shape the research question, technical direction, evaluation, and presentation.

Publications

LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model

2026-05-15 Marcel Mateos Salles, Praney Goyal, Pradyut Sekhsaria, Hai Huang, Randall Balestriero Spotlight, ICLR 2026 Workshop On Principled Design for Trustworthy AI
Paper