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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Delving into Effective Gradient Matching for Dataset Condensation


Jul 30, 2022
Zixuan Jiang, Jiaqi Gu, Mingjie Liu, David Z. Pan

* 12 pages 

   Access Paper or Ask Questions

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

RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL


Jul 13, 2022
Wei Shi, Hanrui Wang, Jiaqi Gu, Mingjie Liu, David Pan, Song Han, Nan Sun


   Access Paper or Ask Questions

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

ELight: Enabling Efficient Photonic In-Memory Neurocomputing with Life Enhancement


Dec 15, 2021
Hanqing Zhu, Jiaqi Gu, Chenghao Feng, Mingjie Liu, Zixuan Jiang, Ray T. Chen, David Z. Pan

* 7 pages, 8 figures, accepted by ASPDAC 2022 

   Access Paper or Ask Questions

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

Towards Memory-Efficient Neural Networks via Multi-Level in situ Generation


Sep 05, 2021
Jiaqi Gu, Hanqing Zhu, Chenghao Feng, Mingjie Liu, Zixuan Jiang, Ray T. Chen, David Z. Pan

* Accepted by International Conference on Computer Vision (ICCV) 2021 

   Access Paper or Ask Questions

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

Optimizer Fusion: Efficient Training with Better Locality and Parallelism


Apr 01, 2021
Zixuan Jiang, Jiaqi Gu, Mingjie Liu, Keren Zhu, David Z. Pan

* It is published as a paper at the Hardware Aware Efficient Training (HAET) workshop of ICLR 2021. There are 4 pages excluding references and appendices 

   Access Paper or Ask Questions

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