Song Han

Song Han is an associate professor at MIT EECS. He received his Ph.D. from Stanford University. He proposed the “Deep Compression” technique including pruning and quantization that is widely used for efficient AI computing, and “Efficient Inference Engine” that first brought weight sparsity to modern AI chips, making it one of the top-5 most cited papers in the 50-year history of ISCA. He pioneered the TinyML research that brings deep learning to IoT devices, enabling learning on the edge. His team’s work on hardware-aware neural architecture search (once-for-all network) enables users to design, optimize, shrink and deploy AI models to resource-constrained hardware devices, receiving the first place in many low-power computer vision contests in flagship AI conferences.
Avatar photo

Posts by Song Han

Decorative image of VILA and Jetson Orin workflow.
Generative AI

Visual Language Intelligence and Edge AI 2.0

VILA is a family of high-performance vision language models developed by NVIDIA Research and MIT. The largest model comes with ~40B parameters and the smallest... 8 MIN READ
Decorative image.
Generative AI

Visual Language Models on NVIDIA Hardware with VILA

Visual language models have evolved significantly recently. However, the existing technology typically only supports one single image. They cannot reason among... 11 MIN READ