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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Picture for Haichuan Yang

Haichuan Yang

University of Rochester

Learning a Dual-Mode Speech Recognition Model via Self-Pruning


Jul 25, 2022
Chunxi Liu, Yuan Shangguan, Haichuan Yang, Yangyang Shi, Raghuraman Krishnamoorthi, Ozlem Kalinli

* 7 pages, 1 figure 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks


Jun 02, 2022
Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin

* Accepted at ICML 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PyTorchVideo: A Deep Learning Library for Video Understanding


Nov 18, 2021
Haoqi Fan, Tullie Murrell, Heng Wang, Kalyan Vasudev Alwala, Yanghao Li, Yilei Li, Bo Xiong, Nikhila Ravi, Meng Li, Haichuan Yang, Jitendra Malik, Ross Girshick, Matt Feiszli, Aaron Adcock, Wan-Yen Lo, Christoph Feichtenhofer

* Technical report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Low-Rank+Sparse Tensor Compression for Neural Networks


Nov 02, 2021
Cole Hawkins, Haichuan Yang, Meng Li, Liangzhen Lai, Vikas Chandra


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet


Oct 15, 2021
Haichuan Yang, Yuan Shangguan, Dilin Wang, Meng Li, Pierce Chuang, Xiaohui Zhang, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Noisy Training Improves E2E ASR for the Edge


Jul 09, 2021
Dilin Wang, Yuan Shangguan, Haichuan Yang, Pierce Chuang, Jiatong Zhou, Meng Li, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework


Aug 25, 2020
Haotao Wang, Shupeng Gui, Haichuan Yang, Ji Liu, Zhangyang Wang

* ECCV 2020 spotlight 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Sparsity and Quantization Jointly and Automatically for Neural Network Compression via Constrained Optimization


Oct 17, 2019
Haichuan Yang, Shupeng Gui, Yuhao Zhu, Ji Liu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adversarially Trained Model Compression: When Robustness Meets Efficiency


Feb 10, 2019
Shupeng Gui, Haotao Wang, Chen Yu, Haichuan Yang, Zhangyang Wang, Ji Liu

* 29 pages, 15 figures, 11 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ECC: Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model


Dec 17, 2018
Haichuan Yang, Yuhao Zhu, Ji Liu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>