Mohamed Elrefaie

Mohamed Elrefaie

PhD Researcher | Mechanical Engineering & Schwarzman College of Computing, MIT

About

I am a PhD researcher at the Massachusetts Institute of Technology (MIT) in the Mechanical Engineering Department and the Schwarzman College of Computing. I hold a B.Sc. in Mechanical Engineering and an M.Sc. in Aerospace Engineering from the Technical University of Munich (TUM).

My research focuses on combining deep learning with computational and experimental fluid dynamics to develop foundation models for physics—AI systems that understand and simulate complex physical phenomena for use in engineering design.

Highlights

TripOptimizer Accepted to Physics of Fluids

Dec 3, 2025

TripOptimizer: Generative 3D Shape Optimization and Drag Prediction using Triplane VAE Networks.

Read Paper →

BlendedNet++ Preprint Released

Dec 3, 2025

Featuring 12,490 aerodynamic high-fidelity simulations.

Read Preprint →

📢 Released CarBench

Nov 26, 2025

A unified benchmark for high-fidelity 3D car aerodynamics.

Three Papers Accepted to IDETC-CIE 2025

May 1, 2025

Covering AI Design Agents, scalable datasets, and blended-wing bodies.

Selected Publications

CarBench Visualization

CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics

Mohamed Elrefaie, Dule Shu, Matt Klenk, Faez Ahmed

Released Nov 2025

TripOptimizer Visualization

TripOptimizer: Generative 3D Shape Optimization and Drag Prediction using Triplane VAE Networks

Parsa Vatani, Mohamed Elrefaie, Farhad Nazarpour, Faez Ahmed

Physics of Fluids, 2025

AI Agents Visualization

AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design

Mohamed Elrefaie, Janet Qian, Raina Wu, Qian Chen, Angela Dai, Faez Ahmed

IDETC-CIE 2025

DrivAerNet++ Visualization

DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Mohamed Elrefaie, Florin Morar, Angela Dai, Faez Ahmed

NeurIPS 2024 (MIT Research Spotlight)

PIV Visualization

Real-time and on-site aerodynamics using stereoscopic piv and deep optical flow learning

Mohamed Elrefaie, Steffen HĂĽttig, Mariia Gladkova, Timo Gericke, Daniel Cremers, Christian Breitsamter

Experiments in Fluids (Springer Nature), 2024