Mohammad Rastegari

Mohammad Rastegari serves as a senior technical manager in Apple's AI/ML organization and holds an affiliate assistant professor position in the Computer Science and Engineering Department at the University of Washington. Previously, he was a research scientist at the Allen Institute for AI (AI2) where he contributed to the PRIOR team, and co-founded XNOR.ai as Chief Technology Officer.

He completed his Ph.D. at the University of Maryland under the supervision of Professor Larry S. Davis, focusing on computer vision and machine learning.

His research centers on efficient deep learning with major contributions in binary neural networks (notably XNOR-Networks for resource-constrained devices) and model compression. Current work extends to large language model efficiency through weight clustering, token pruning, and memory optimization while maintaining strong foundations in computer vision.

Analysis of his recent publications reveals a strategic shift toward optimizing transformer-based architectures across vision and language domains, with consistent emphasis on deployable solutions for edge computing and real-world applications.

He co-founded XNOR.ai (acquired by Apple) and contributed to AI2's PRIOR initiative, demonstrating a career trajectory bridging academic innovation and industrial implementation in efficient AI systems.