UT Austin ECE · Ph.D. student

Mohamad Chehade

Reliable learning systems for decisions under uncertainty.

My research develops risk-aware and verifiable learning methods, so that decisions under uncertainty can be made with explicit risk specifications and, where possible, testable guarantees. The work spans reinforcement learning, inference-time alignment of large language models, verification of neural networks, and applications to power-system operation and control.

I am a Ph.D. student in Electrical and Computer Engineering at The University of Texas at Austin, advised by Prof. Hao Zhu. I received my B.Eng. in ECE with a minor in Mathematics from the American University of Beirut, where I worked with Prof. Rabih Jabr and Prof. Sami Karaki, and I have interned at Los Alamos National Laboratory with Dr. Wenting Li, Dr. Brian Bell, and Dr. Russell Bent, and at Argonne National Laboratory with Dr. Feng Qiu and Dr. Wei Gao.

Research

Research directions

Explore all research

Research thesis

Reliable learning systems treat risk as a first-class learning objective and verifiability as a deployable property — not a post-hoc check — so that decisions under uncertainty can carry explicit guarantees in reliability-critical domains such as power-system operation.

Selected Publications

Recent papers

View all publications

Recent activity

Recent activity

Awarded third place at the ASME CIE 2026 Student Hackathon, a competition focused on AI for engineering design and manufacturing, organized by the American Society of Mechanical Engineers (ASME) and its Computer & Information in Engineering (CIE) Division.
NEO-Grid accepted to HICSS 2026.