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 Yingyan Lin

FBNetV5: Neural Architecture Search for Multiple Tasks in One Run


Nov 19, 2021
Bichen Wu, Chaojian Li, Hang Zhang, Xiaoliang Dai, Peizhao Zhang, Matthew Yu, Jialiang Wang, Yingyan Lin, Peter Vajda


  Access Paper or Ask Questions

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks


Nov 06, 2021
Yonggan Fu, Qixuan Yu, Yang Zhang, Shang Wu, Xu Ouyang, David Cox, Yingyan Lin

* Accepted at NeurIPS 2021 

  Access Paper or Ask Questions

RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms


Nov 04, 2021
Yongan Zhang, Anton Banta, Yonggan Fu, Mathews M. John, Allison Post, Mehdi Razavi, Joseph Cavallaro, Behnaam Aazhang, Yingyan Lin

* JETC Special issue on Hardware-Aware Learning for Medical Applications (Waiting assignment to batch) 

  Access Paper or Ask Questions

2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency


Sep 21, 2021
Yonggan Fu, Yang Zhao, Qixuan Yu, Chaojian Li, Yingyan Lin

* Accepted at MICRO 2021 

  Access Paper or Ask Questions

G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency


Sep 18, 2021
Yongan Zhang, Haoran You, Yonggan Fu, Tong Geng, Ang Li, Yingyan Lin

* Accepted at ICCAD 2021 

  Access Paper or Ask Questions

O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed


Aug 17, 2021
Mengquan Li, Zhongzhi Yu, Yongan Zhang, Yonggan Fu, Yingyan Lin

* Accepted at ICCAD 2021 

  Access Paper or Ask Questions

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference


Jul 16, 2021
Chaojian Li, Wuyang Chen, Yuchen Gu, Tianlong Chen, Yonggan Fu, Zhangyang Wang, Yingyan Lin

* 16 pages, 6 figures 

  Access Paper or Ask Questions

A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning


Jun 11, 2021
Yonggan Fu, Yongan Zhang, Chaojian Li, Zhongzhi Yu, Yingyan Lin

* Accepted at DAC 2021. arXiv admin note: text overlap with arXiv:2012.13091 

  Access Paper or Ask Questions

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators


Jun 11, 2021
Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox, Yingyan Lin

* Accepted at ICML 2021 

  Access Paper or Ask Questions

InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks


Apr 22, 2021
Yonggan Fu, Zhongzhi Yu, Yongan Zhang, Yifan Jiang, Chaojian Li, Yongyuan Liang, Mingchao Jiang, Zhangyang Wang, Yingyan Lin

* Accepted at DAC 2021 

  Access Paper or Ask Questions

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark


Mar 19, 2021
Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Yingyan Lin

* Accepted at ICLR 2021 (Spotlight) 

  Access Paper or Ask Questions

GEBT: Drawing Early-Bird Tickets in Graph Convolutional Network Training


Mar 01, 2021
Haoran You, Zhihan Lu, Zijian Zhou, Yingyan Lin


  Access Paper or Ask Questions

CPT: Efficient Deep Neural Network Training via Cyclic Precision


Jan 25, 2021
Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin

* Accepted at ICLR 2021 (Spotlight) 

  Access Paper or Ask Questions

Max-Affine Spline Insights Into Deep Network Pruning


Jan 07, 2021
Randall Balestriero, Haoran You, Zhihan Lu, Yutong Kou, Yingyan Lin, Richard Baraniuk


  Access Paper or Ask Questions

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training


Jan 04, 2021
Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang

* arXiv admin note: substantial text overlap with arXiv:2005.03403 

  Access Paper or Ask Questions

Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search


Dec 25, 2020
Yonggan Fu, Zhongzhi Yu, Yongan Zhang, Yingyan Lin


  Access Paper or Ask Questions

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training


Dec 24, 2020
Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan Lin

* Accepted at NeurIPS 2020 

  Access Paper or Ask Questions

DNA: Differentiable Network-Accelerator Co-Search


Oct 28, 2020
Yongan Zhang, Yonggan Fu, Weiwen Jiang, Chaojian Li, Haoran You, Meng Li, Vikas Chandra, Yingyan Lin


  Access Paper or Ask Questions

ShiftAddNet: A Hardware-Inspired Deep Network


Oct 24, 2020
Haoran You, Xiaohan Chen, Yongan Zhang, Chaojian Li, Sicheng Li, Zihao Liu, Zhangyang Wang, Yingyan Lin

* Accepted by NeurIPS 2020 

  Access Paper or Ask Questions

AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks


Jul 06, 2020
Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li, Yingyan Lin, Zhangyang Wang

* Accepted at ICML2020 

  Access Paper or Ask Questions

AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles


Jun 08, 2020
Sicong Liu, Junzhao Du, Kaiming Nan, ZimuZhou, Atlas Wang, Yingyan Lin

* IEEE transactions on mobile computing, 2020 

  Access Paper or Ask Questions

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation


May 08, 2020
Yang Zhao, Xiaohan Chen, Yue Wang, Chaojian Li, Haoran You, Yonggan Fu, Yuan Xie, Zhangyang Wang, Yingyan Lin

* Accepted by 47th International Symposium on Computer Architecture (ISCA'2020) 

  Access Paper or Ask Questions

TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domain


May 03, 2020
Weitao Li, Pengfei Xu, Yang Zhao, Haitong Li, Yuan Xie, Yingyan Lin

* Accepted by 47th International Symposium on Computer Architecture (ISCA'2020) 

  Access Paper or Ask Questions

A New MRAM-based Process In-Memory Accelerator for Efficient Neural Network Training with Floating Point Precision


Mar 02, 2020
Hongjie Wang, Yang Zhao, Chaojian Li, Yue Wang, Yingyan Lin

* Accepted by the IEEE International Symposium on Circuits and Systems 2020 (ISCAS'2020) 

  Access Paper or Ask Questions

DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architectures


Feb 26, 2020
Yang Zhao, Chaojian Li, Yue Wang, Pengfei Xu, Yongan Zhang, Yingyan Lin

* Accepted by 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2020) 

  Access Paper or Ask Questions

AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs


Jan 06, 2020
Pengfei Xu, Xiaofan Zhang, Cong Hao, Yang Zhao, Yongan Zhang, Yue Wang, Chaojian Li, Zetong Guan, Deming Chen, Yingyan Lin

* Accepted by 28th ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA'2020) 

  Access Paper or Ask Questions