World's Best Scientists 2026 revealed!
Song Han

Song Han

Award Badge
Rising Stars
2025

D-Index & Metrics

Rising Stars

D-Index
53
Citations
44758
World Ranking
236
National Ranking
35

Computer Science

D-Index
54
Citations
47121
World Ranking
4418
National Ranking
2062

Research.com Recognitions

  • 2025 - Research.com Rising Stars Award

Overview

Song Han is affiliated with MIT in the United States and has made contributions primarily in the fields of computer science and engineering. Their research focuses on areas including computer vision and pattern recognition, artificial intelligence, electrical and electronic engineering, aerospace engineering, and computer networks and communications.

The scientist's work encompasses multiple topics, such as advanced neural network applications, quantum computing algorithms and architecture, quantum information and cryptography, human pose and action recognition, adversarial robustness in machine learning, video surveillance and tracking methods, and domain adaptation and few-shot learning.

Song Han has published extensively, with a notable presence in venues such as arXiv (Cornell University), IEEE Transactions on Pattern Analysis and Machine Intelligence, Applied Intelligence, Proceedings of the 59th ACM/IEEE Design Automation Conference, and IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

  • Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey, 2020, Proceedings of the IEEE
  • MCUNet: Tiny Deep Learning on IoT Devices, 2020, arXiv (Cornell University)
  • Domain-specific hardware accelerators, 2020, Communications of the ACM
  • Lite Transformer with Long-Short Range Attention, 2020, arXiv (Cornell University)
  • Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications, 2022, ACM Transactions on Design Automation of Electronic Systems

Frequent coauthors of Song Han include Zhijian Liu, Ji Lin, Hanrui Wang, Yujun Lin, and Jiaqi Gu.

The range of Song Han's research venues and collaboration networks reflects involvement in diverse topics primarily related to neural networks, hardware acceleration, and deep learning on resource-constrained devices.

Best Publications

  • Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

    Song Han;Huizi Mao;William J. Dally;William J. Dally

  • SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

    Forrest N. Iandola;Song Han;Matthew W. Moskewicz;Khalid Ashraf

  • Learning both weights and connections for efficient neural networks

    Song Han;Jeff Pool;John Tran;William J. Dally

  • EIE: efficient inference engine on compressed deep neural network

    Song Han;Xingyu Liu;Huizi Mao;Jing Pu

  • TSM: Temporal Shift Module for Efficient Video Understanding

    Ji Lin;Chuang Gan;Song Han

  • ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

    Han Cai;Ligeng Zhu;Song Han

  • AMC: AutoML for Model Compression and Acceleration on Mobile Devices

    Yihui He;Ji Lin;Zhijian Liu;Hanrui Wang

  • Deep Leakage from Gradients

    Ligeng Zhu;Zhijian Liu;Song Han

  • Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

    Yujun Lin;Song Han;Huizi Mao;Yu Wang

  • HAQ: Hardware-Aware Automated Quantization With Mixed Precision

    Kuan Wang;Zhijian Liu;Yujun Lin;Ji Lin

  • Trained Ternary Quantization

    Chenzhuo Zhu;Song Han;Huizi Mao;William J. Dally

  • Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey

    Lei Deng;Guoqi Li;Song Han;Luping Shi

  • Once for All: Train One Network and Specialize it for Efficient Deployment

    Han Cai;Chuang Gan;Tianzhe Wang;Zhekai Zhang

  • ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA

    Song Han;Junlong Kang;Huizi Mao;Yiming Hu

  • Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

    Haotian Tang;Zhijian Liu;Shengyu Zhao;Shengyu Zhao;Yujun Lin

  • Angel-Eye: A Complete Design Flow for Mapping CNN Onto Embedded FPGA

    Kaiyuan Guo;Lingzhi Sui;Jiantao Qiu;Jincheng Yu

  • Fast inference of deep neural networks in FPGAs for particle physics

    Javier Duarte;Edward Kreinar;Maurizio Pierini;Nhan Tran

  • Point-Voxel CNN for Efficient 3D Deep Learning

    Zhijian Liu;Haotian Tang;Yujun Lin;Song Han

  • Differentiable Augmentation for Data-Efficient GAN Training

    Shengyu Zhao;Zhijian Liu;Ji Lin;Jun-Yan Zhu

  • Fast inference of deep neural networks in FPGAs for particle physics

    Javier Duarte;Song Han;Philip Harris;Sergo Jindariani

  • MCUNet: Tiny Deep Learning on IoT Devices

    Ji Lin;Wei-Ming Chen;Yujun Lin;john cohn

Frequent Co-Authors

William J. Dally
William J. Dally Nvidia (United Kingdom)
Chuang Gan
Chuang Gan University of Massachusetts Amherst
Jun-Yan Zhu
Jun-Yan Zhu Carnegie Mellon University
Huazhong Yang
Huazhong Yang Tsinghua University
Bryan Catanzaro
Bryan Catanzaro Nvidia (United States)
Mark Horowitz
Mark Horowitz Stanford University
Peter Bailis
Peter Bailis Stanford University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA often reveals a wide spectrum of related academic and career pathways. Many students opt for flexible learning through accredited online programs, allowing for better work-life balance and accessibility.

If advancing quickly into the workforce is your goal, pursuing one of the easy associate degrees can provide foundational skills and quicker job entry. For those aiming for advanced expertise, enrolling in online affordable master's programs in computer science or technology-related fields offers specialization without substantial financial burden.

Future leaders might consider the online doctorate in organizational leadership, which prepares graduates to manage teams and drive change in tech organizations. Additionally, those passionate about shaping education might pursue the ed d in education, offering paths toward educational technology, policy, and administration roles.

Whatever your aspirations, the flexible online environment and diverse program offerings empower students to curate the educational journey that best aligns with their personal and professional goals.

Best Scientists Citing Song Han

Trending Scientists

Recently Published Articles