Contributed to several IBM tools and platforms such as In-context Explainability 360, Watsonx.governance, etc.; authored books on introduction to foundation models and adversarial robustness for machine learning; organized or presented tutorials in top-tier conferences (including ICML, KDD, NeurIPS, etc.); served as area chair/senior PC member for numerous leading AI conferences.
Research Experience
Leads the Trusted AI Group at IBM Thomas J. Watson Research Center and serves as a PI for the MIT-IBM Watson AI Lab.
Education
No specific education background information provided.
Background
Principal Research Scientist at IBM Research AI; PI of MIT-IBM Watson AI Lab and RPI-IBM AIRC; Chief Scientist of the RPI-IBM AI Research Collaboration program. Recent research focuses on AI safety and robustness, and more broadly, making AI trustworthy.
Miscellany
Open to collaboration with highly motivated researchers; his work has been widely covered by media, spanning topics from AI safety and robustness to scientific discovery.