Associate Professor · AI Research Leader
Making agentic AI robust, reliable, and deployable, from the frontier to the edge.
I build AI systems that hold up when it matters: agentic systems that know when they might be wrong, models compressed to run at the edge, and rigorous methods for telling a real result from a lucky one.

Research thrusts
Robust & Reliable Visual Agentic Systems
Agents that perceive and act, and know when they might be wrong.
Efficient AI at the Edge
Compress capable models to run under real latency and power limits.
Uncertainty, Assurance & Trust
Rigorous measurement: telling a real result from a lucky one.
Current work
News
All news- Nov 2026
Can a drone tell when a car is going the wrong way, in heavy rain?
A short research teaser: testing drone sensing on simulated city streets in rain, glare and low sun, and trying to break it on purpose.
- Nov 2026
Our paper at the NeurIPS 2026 AI for Science Workshop
"Your Research Loop Is Measuring Noise: Accept Rules for Autonomous Experimentation", with Venkat R. Dasari, is final for the NeurIPS 2026 AI for Science Workshop. Poster in Sydney on December 12.
- Oct 2026
Co-chaired the LEAF workshop at IEEE MILCOM 2026
I co-chaired LEAF (Lightweight Edge-Adaptive Foundation Models for Intelligence and Autonomous Reasoning), Workshop 4 at IEEE MILCOM 2026 in the Washington, DC area, with Venkat Dasari and Peng Wang of DEVCOM ARL. The program had eleven papers on compressing and deploying foundation models at the tactical edge, including two posters from our group: GOE and Measure, Then Compress.
Work with me