UT Austin ECE / Reliable learning systems

Mohamad Chehade

Reliable machine learning for risk, constraints, and decisions.

I am a Ph.D. student in Electrical and Computer Engineering at The University of Texas at Austin, advised by Prof. Hao Zhu. My research develops risk-aware and verifiable learning methods for decision-making under uncertainty, with applications in reinforcement learning, large language models, and power systems.

I received my B.Eng. in Electrical and Computer Engineering, with a minor in Mathematics, from the American University of Beirut, where I worked with Prof. Rabih Jabr and Prof. Sami Karaki. I have also interned at Los Alamos National Laboratory with Dr. Wenting Li, Dr. Brian Bell, and Dr. Russell Bent.

Home UT Austin ECE
Recent ICML 2025
Methods RL / LLMs / Verification
Applications Power systems

Research

Research direction

From uncertainty quantification to deployment in reliability-critical systems.

01

Measure risk

Model uncertainty, distribution shift, and downside outcomes before learned systems make decisions.

02

Verify reliability

Build verification and stress-testing tools for learned models in constrained technical domains.

03

Deploy with constraints

Translate RL and LLM methods into actionable decisions for systems where failures are expensive.

Selected Publications

Recent papers

View all publications

News

Recent updates

Two papers accepted to the 2026 IEEE Power & Energy Society General Meeting.
NEO-Grid accepted to HICSS 2026.
Papers LEVIS and SITAlign accepted to ICML 2025.
Awarded Best Graduate Presentation Award at NAPS 2024.