Hanrui Wang

profile photo

Hanrui Wang
hanrui AT mit.edu

Hello and Welcome! You can call me Hank. I am currently a Ph.D. Student at MIT, advised by Prof. Song Han.

Previously, I received my Master from MIT in 2020 and Bachelor from Fudan University in 2018. During my undergrad, I was fortunate to work with Prof. Jason Cong, Prof. C.-J. Richard Shi, Prof. Xiaoyang Zeng and Prof. Yibo Fan.

My research area is the intersection of Computer Architecture, Quantum Computing and Machine Learning.

GitHub  /  Google Scholar  /  LinkedIn  /  Twitter  /  YouTube

News
  • Feb. 2021. SpAtten project is selected as MIT homepage spotlight.
  • Jan. 2021. Got awarded Baidu Scholarship.
  • Dec. 2020. Got awarded Analog Devices outstanding student designer.
  • Nov. 2020. Got awarded Nvidia Graduate Fellowship Finalist.
Publications[Full List]
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
Hanrui Wang, Zhekai Zhang, Song Han
International Symposium on High-Performance Computer Architecture (HPCA), 2021.
Paper  /  Slides  /  Intro Video  /  Short Video  /  Project Page

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
Hanrui Wang, Zhanghao Wu, Zhijian Liu, Han Cai, Ligeng Zhu, Chuang Gan, Song Han
Annual Conference of the Association for Computational Linguistics (ACL), 2020.
Paper  /  Slides  /  Video  /  Code  /  Project Page

GCN-RL Circuit Designer: Transferable Transistor Sizing With Graph Neural Networks and Reinforcement Learning
Hanrui Wang, Kuan Wang, Jiacheng Yang, Linxiao Shen, Nan Sun, Hae-Seung Lee, Song Han
Design Automation Conference (DAC), 2020.
Paper  /  Slides  /  Poster  /  Video  /  Project Page

SpArch: Efficient Architecture for Sparse Matrix Multiplication
Zhekai Zhang*, Hanrui Wang* , Song Han, William J. Dally (*Equal Contributions)
International Symposium on High-Performance Computer Architecture (HPCA), 2020
Paper  /  2-min Intro  /  Intro  /  Talk  /  Slides  /  Project Page

MicroNet for Efficient Language Modeling
Zhongxia Yan, Hanrui Wang, Demi Guo, Song Han
Journal of Machine Learning Research, 2020.
Paper  /  Talk (Starts from 26:17)  /  Code  /  Project Page

Park: An Open Platform for Learning-Augmented Computer Systems
Hongzi Mao, Parimarjan Negi, Akshay Narayan, Hanrui Wang, Jiacheng Yang, Haonan Wang, Ryan Marcus, ravichandra addanki, Mehrdad Khani Shirkoohi, Songtao He, Vikram Nathan, Frank Cangialosi, Shaileshh, Venkatakrishnan, Wei-Hung Weng, Song Han, Tim Kraska, Mohammad Alizadeh
Advances in Neural Information Processing Systems (NeurIPS), 2019
Paper  /  Code

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
Tianzhe Wang, Kuan Wang, Han Cai, Ji Lin, Zhijian Liu, Hanrui Wang, Yujun Lin, Song Han
Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Paper

Learning to Design Circuits
Hanrui Wang*, Jiacheng Yang*, Hae-Seung Lee, Song Han (*Equal Contributions)
Advances in Neural Information Processing Systems (NeurIPS) Workshop on ML for Systems, 2018
Paper  /  Project Page

AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Yihui He*, Ji Lin*, Zhijian Liu, Hanrui Wang, Li-Jia Li, Song Han (*Equal Contributions)
The European Conference on Computer Vision (ECCV), 2018
Paper  /  Code  /  Models  /  Project Page

Understanding Performance Differences of FPGAs and GPUs
Jason Cong, Zhenman Fang, Michael Lo, Hanrui Wang, Jingxian Xu, Shaochong Zhang (Alphabetical Order)
International Symposium On Field-Programmable Custom Computing Machines (FCCM), 2018
Paper
Honors and Awards
  • 2021 Baidu Graduate Scholarship
  • 2021 Analog Devices Outstanding Student Designer Award
  • 2020 Nvidia Graduate Fellowship Finalist
  • 2020 DAC Young Fellowship & Young Fellow Best Presentation Award
  • 2019 Champion of NeurIPS 2019 MicroNet efficient Language Model Competition
  • 2019 Best Paper Award of ICML 2019 Reinforcement Learning for Real Life Workshop
  • 2018 Bronze Medal in Kaggle TensorFlow Speech Recognition Challenge
  • 2017 UCLA CSST Fellowship & CSST Best Research Award
  • 2016 Chun-Tsung Research Fellowship
  • 2015/2016/2017 China National Scholarship
Talks
Efficient Natural Language Processing
Machine Learning for Analog Circuit Design
Efficient Sparse Matrix Multiplication Accelerator
Services
Reviewer for ACL, JMLR, TCAS-II, TODAES, TNNLS, MLR, ICITED