Song Han

Assistant Professor, MIT EECS

Efficient AI

with Tiny Resource

Accelerate Deep Learning Computing


Song Han is an assistant professor in MIT’s Department of Electrical Engineering and Computer Science. He received his PhD degree from Stanford University. His research focuses on efficient deep learning computing. He proposed “deep compression” technique that can reduce neural network size by an order of magnitude without losing accuracy, and the hardware implementation “efficient inference engine” that first exploited pruning and weight sparsity in deep learning accelerators. His recent work on hardware-aware neural architecture search was highlighted by MIT NewsQualcomm NewsVentureBeatIEEE Spectrum, integrated in PyTorch and AutoGluon, and received many low-power computer vision contest awards in flagship AI conferences (CVPR’19, ICCV’19 and NeurIPS’19). Song received Best Paper awards at ICLR’16 and FPGA’17, Amazon Machine Learning Research Award, SONY Faculty Award, Facebook Faculty Award. Song was named “35 Innovators Under 35” by MIT Technology Review for his contribution on “deep compression” technique that “lets powerful artificial intelligence (AI) programs run more efficiently on low-power mobile devices.” Song received the NSF CAREER Award for “efficient algorithms and hardware for accelerated machine learning.”

Research Interests

Efficient algorithms and hardware for computation-intensive AI applications. 
We actively collaborate with industry partners. 

Model Compression / AutoML / NAS: [ICLR’20][CVPR’20][ICLR’19][CVPR’19, oral][ECCV’18][ICLR’16, BP][NIPS’15]
Efficient AI Applications: Video / Point Cloud / NLP [ICLR’20][CVPR’20][NeurIPS’19, spotlight][ICCV’19]
HW for ML: [HPCA’20][FPGA’17, BP][ISCA’16]
ML for HW: [DAC’20][NeurIPS’19 W]
Secure AI: [NeurIPS’19][ICLR’19]

I am looking for PhD and UROP students who are interested in:
H: High performance, High energy efficiency Hardware
A: AutoML, Architectures and Accelerators for AI
N: Novel applications with Neural Networks

YouTube, Twitter, Google Scholar, Github, LinkedIn, Group Website


  • NSF CAREER Award, 2020
  • NVIDIA Academic Partnership Award, 2020
  • MIT Technology Review list of 35 Innovators Under 35, 2019
  • SONY Faculty Award, 2017/2018
  • Amazon Machine Learning Research Award, 2018/2019
  • Facebook Research Award, 2019
  • Best paper award, FPGA’2017
  • Best paper award, ICLR’2016

Competition Awards




Ph.D. Stanford University, advised by Prof. Bill Dally

B.S. Tsinghua University


Email: FirstnameLastname [at] mit [dot] edu

Scroll Up