Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Aug 13, 2020
Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han

* ECCV 2020. The first two authors contributed equally to this work. Project page: http://spvnas.mit.edu/ 

  Access Paper or Ask Questions

Hardware-Centric AutoML for Mixed-Precision Quantization

Aug 11, 2020
Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han

* International Journal of Computer Vision (IJCV), 2020 
* Journal preprint of arXiv:1811.08886 (IJCV, 2020). The first three authors contributed equally to this work. Project page: https://hanlab.mit.edu/projects/haq/ 

  Access Paper or Ask Questions

MCUNet: Tiny Deep Learning on IoT Devices

Jul 20, 2020
Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, Song Han

* Demo video available here: https://youtu.be/YvioBgtec4U 

  Access Paper or Ask Questions

Lite Transformer with Long-Short Range Attention

Apr 24, 2020
Zhanghao Wu, Zhijian Liu, Ji Lin, Yujun Lin, Song Han

* ICLR 2020. The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Point-Voxel CNN for Efficient 3D Deep Learning

Jul 08, 2019
Zhijian Liu, Haotian Tang, Yujun Lin, Song Han

* The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Design Automation for Efficient Deep Learning Computing

Apr 24, 2019
Song Han, Han Cai, Ligeng Zhu, Ji Lin, Kuan Wang, Zhijian Liu, Yujun Lin


  Access Paper or Ask Questions

HAQ: Hardware-Aware Automated Quantization

Dec 06, 2018
Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han

* The first three authors contributed equally to this work. Project page: https://hanlab.mit.edu/projects/haq/ 

  Access Paper or Ask Questions

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

Feb 05, 2018
Yujun Lin, Song Han, Huizi Mao, Yu Wang, William J. Dally

* ICLR 2018 
* we find 99.9% of the gradient exchange in distributed SGD is redundant; we reduce the communication bandwidth by two orders of magnitude without losing accuracy 

  Access Paper or Ask Questions