Biography

I am currently a tenure-track assistant professor jointly affiliated with Institute for Artificial Intelligence and School of Integrated Circuits in Peking University. Before joining Peking University, I was a staff research scientist and tech lead in Meta On-Device AI team with a focus on researching and productizing efficient AI algorithms and hardwares for next generation AR/VR devices. I received my Ph.D. degree in the Department of Electrical and Computer Engineering, University of Texas at Austin under the supervision of Prof. David Z. Pan and my bachelor degree in Peking University under the supervision of Prof. Ru Huang and Prof. Runsheng Wang.

My research interests focus on efficient multi-modality AI acceleration algorithms and hardwares.

I am always looking for creative and self-motivated students and post docs who are interested in co-designing the future AI acceleration system. Please contact me via email with the subject line “Perspective Student from [Your Institute]” and your CV.

Download my resumé.

Interests
  • Efficient and Secure Multi-Modality Artificial Intelligence
  • Algorithm/Hardware Co-Design/Co-Optimization
Education

  • PhD in Computer Engineering, 2018

    University of Texas at Austin, Austin, Tx, USA

  • MS in Computer Engineering, 2015

    University of Texas at Austin, Austin, Tx, USA

  • BS in Microelectronics, 2013

    Peking University, Beijing, China

Research Focus

Efficient AI Algorithm
Multi-Modal AI
AI/HW Co-Design

News

One Paper Accepted in NeurIPS 2022
One paper on “BiT{:} Robustly Binarized Multi-distilled Transformer” is accepted by NeurIPS'2022.
Last updated on Sep 27, 2022
One Paper Accepted in ICML 2022
One paper on “DepthShrinker{:} A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks” is accepted by ICML'2022.
Last updated on May 19, 2022
One Paper Accepted in IJCAI-ECAI 2022
One paper on “Decentralized Unsupervised Learning of Visual Representations” is accepted by the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI'2022).
Last updated on May 18, 2022
Two Papers Accepted in CVPR 2022
Two papers on “Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation” and “SplitNets{:} Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems” are accepted by CVPR'2022.
Last updated on Mar 5, 2022
One Paper Accepted in ICASSP 2022
One paper on “Omni-sparsity DNN{:} Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet” is accepted by ICASSP'2022.
Last updated on Mar 15, 2022

Experience

 
 
 
 
 
Tenure-Track Assistant Professor
Peking University
Jul 2022 – Present Beijing
Institute of Artificial Intelligence
 
 
 
 
 
Staff Research Scientist
Meta
Sep 2018 – Jul 2022 California

Responsibilities include:

  • Tech Lead, On-Device AI, Meta Reality Lab
  • Efficient NN for AR Glasses
  • Efficient NN/HW Co-Design/Co-Optimization
 
 
 
 
 
Research Intern
arm
May 2017 – Aug 2017 California
Privacy-preserving neural network training, including federated learning with non-IID data and PrivyNet with split network architectures
 
 
 
 
 
Research Intern
arm
May 2016 – Aug 2016 California
Cross-level monte carlo framework for system vulnerability evaluation against fault attack
 
 
 
 
 
Research & Design Intern
Cadence Design System
May 2014 – Aug 2014 California
Static timing analysis acceleration

Recent Talks

Efficient Audio-Visual Understanding on AR Devices
Discuss full stack techniques from training, optimization, hardware, etc perspectives to enable efficient audio-visual understanding on AR devices
Nov 5, 2021 11:00 AM — 12:00 PM
Efficient Audio-Visual Understanding on AR Devices
Discuss full stack techniques from training, optimization, hardware, etc perspectives to enable efficient audio-visual understanding on AR devices
Apr 27, 2021 11:00 AM — 12:00 PM
Improving Weight-Sharing NAS with Better Search Space and Better Supernet Training
Discuss our recent progress on improving the weight-sharing NAS by designing better search space and better supernet training algorithms
Apr 20, 2021 11:00 AM — 12:00 PM

Recent Publications

More detailed publication lists available through Google Scholar

Quickly discover relevant content by filtering publications.
Zechun Liu, Barlas Oguz, Aasish Pappu, Lin Xiao, Scott Yih, Meng Li, Raghuraman Krishnamoorthi, Yashar Mehdad (2022). BiT: Robustly Binarized Multi-distilled Transformer. In Conference on Neural Information Processing Systems (NeurIPs) 2022.

PDF

Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin (2022). Depth Shrink: Empowering Hardware-Friendly Shallow Neural Networks. In Conference on Machine Learning (ICML) 2022.

PDF

Haichuan Yang, Yuan Shangguan, Dilin Wang, Meng Li, Pierce Chuang, Xiaohui Zhang, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra (2022). Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet. In International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022.

PDF

Jiaqi Gu, Hyoukjun Kwon, Dilin Wang, Wei Ye, Meng Li, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra, David Pan (2022). Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation. In Conference on Computer Vision and Pattern Recognition (CVPR) 2022.

PDF

Xin Dong, Ziyun Li, Meng Li, Zhongnan Qu, Barbara De Salvo, Chiao Liu, Hsiang-Tsung Kung (2022). SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems. In Conference on Computer Vision and Pattern Recognition (CVPR) 2022.

Chengyue Gong, Dilin Wang, Meng Li, Xinlei Chen, Zhicheng Yan, Yuandong Tian, Qiang Liu, Vikas Chandra (2022). NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training. In Conference on Learning Representations (ICLR) 2022.

PDF

Yongan Zhang, Yonggan Fu, Weiwen Jiang, Chaojian Li, Haoran You, Meng Li, Vikas Chandra, Yingyan Lin (2021). DNA: Differentiable Network-Accelerator Co-Search. In International Symposium on Low Power Electronics and Design (ISLPED) 2021.

PDF

Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra (2021). AlphaNet: Improved Training of Supernets with Alpha-Divergence. In Conference on Machine Learning (ICML) 2021 (Long Oral).

PDF

Dilin Wang, Meng Li, Chengyue Gong, Vikas Chandra (2021). AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling. In Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

PDF

Meng Li, Yilei Li, Vikas Chandra (2021). Improving efficiency in neural network accelerator using operands hamming distance optimization. In Asia and South Pacific Design Automation Conference (ASP-DAC) 2021.

PDF

Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, Qiang Liu (2020). KeepAugment: A Simple Information-Preserving Data Augmentation Approach. In Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

PDF

Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi (2020). Co-exploration of neural architectures and heterogeneous asic accelerator designs targeting multiple tasks. In ACM/IEEE Design Automation Conference (DAC) 2020.

PDF

Meng Li, Kaveh Shamsi, Yier Jin, David Z Pan (2018). TimingSAT: Decamouflaging timing-based logic obfuscation. In IEEE International Test Conference (ITC) 2018.

PDF

Meng Li, David Z. Pan (2018). A Synergistic Framework for Hardware IP Privacy and Integrity Protection. In Springer (2018).

PDF

Meng Li, Bei Yu, Yibo Lin, Xiaoqing Xu, Wuxi Li, David Z. Pan (2018). A Practical Split Manufacturing Framework for Trojan Prevention via Simultaneous Wire Lifting and Cell Insertion. In IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2018).

PDF

Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, Vikas Chandra (2018). Federated Learning with Non-IID Data. In arXiv:1806.00582 (2018).

PDF

Meng Li, Bei Yu, Yibo Lin, Xiaoqing Xu, Wuxi Li, David Z. Pan (2018). A Practical Split Manufacturing Framework for Trojan Prevention via Simultaneous Wire Lifting and Cell Insertion. In Asia and South Pacific Design Automation Conference (ASP-DAC) 2018.

PDF

Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Z. Pan (2018). PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training. In arXiv:1709:06161 (2018).

PDF

Meng Li, Kaveh Shamsi, Travis Meade, Zheng Zhao, Bei Yu, Yier Jin, David Z Pan (2017). Provably secure camouflaging strategy for IC protection. In ACM/IEEE International Conference on Computer Aided Design (ICCAD) 2017.

PDF

Meng Li, Kaveh Shamsi, Travis Meade, Zheng Zhao, Bei Yu, Yier Jin, David Z Pan (2017). Provably secure camouflaging strategy for IC protection. In IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2018).

PDF

Meng Li, Liangzhen Lai, Vikas Chandra, David Z. Pan (2017). Cross-level monte carlo framework for system vulnerability evaluation against fault attack. In ACM/IEEE Design Automation Conference (DAC) 2017.

PDF

Kaveh Shamsi, Meng Li, Travis Meade, Zheng Zhao, David Z Pan, Yier Jin (2017). AppSAT: Approximately Deobfuscating Integrated Circuits. In IEEE International Symposium on Hardware Oriented Security and Trust (HOST) 2017 (Best Paper Award).

PDF

Meng Li, Ye Wang, Michael Orshansky (2016). A monte carlo simulation flow for seu analysis of sequential circuits. In ACM/IEEE Design Automation Conference (DAC) 2016.

PDF

Meng Li, Jin Miao, Kai Zhong, David Z Pan (2016). Practical public PUF enabled by solving max-flow problem on chip. In ACM/IEEE Design Automation Conference (DAC) 2016.

PDF

Meng Li, Runsheng Wang, Jibin Zou, Ru Huang (2013). Characterization of Random Telegraph Noise in Scaled High-κ/Metal-Gate MOSFETs with SiO2/HfO2 Gate Dielectrics. In ECS Transactions, 52 (1) 941-946 (2013).

PDF

Projects

*
All Deep Learning Security Other
Last updated on May 18, 2022
NASViT: Neural Architecture Search for Efficient Vision Transformer with Gradient Conflict-Aware Supernet Training

Propose gradient conflict-aware training to improve supernet-based NAS and develop a family of optimized hybrid CNN/ViT networks that achieve state-of-the-art performance Pareto.
Last updated on Mar 5, 2022
AlphaNet: Improved Training of Supernet with Alpha-Divergence

Develop AlphaNet to improve the supernet-based NAS with a more generalized alpha-divergence-based knowledge distillation and achieve state-of-the-art performance Pareto.
Last updated on Mar 5, 2022
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

Develop AttentiveNAS that focuses on improving the sampling strategy for supernet-based NAS to achieve state-of-the-art performance Pareto.

Accomplish­ments

Margarida Jacome Outstanding Dissertation Prize
University of Texas at Austin May 2019
Outstanding Dissertations Award
European Design and Automation Association (EDAA) May 2019
Nominee of ACM Doctoral Dissertation Award
University of Texas at Austin Mar 2019
First Place, Student Research Competition Grand Final (Graduate Category)
Aossication of Computing Machinery (ACM) Jun 2018
Best Paper Award
ACM Great Lake Symposium on VLSI (GLSVLSI) Mar 2018
Best Poster (Presentation) Award
ASPDAC Student Research Forum, Aossication of Computing Machinery (ACM) SIGDA Feb 2018
Gold Medal
ICCAD Student Research Competition, Aossication of Computing Machinery (ACM) SIGDA Nov 2017
Best Paper Award
IEEE International Symposium on Hardware Oriented Security and Trust (HOST) Jul 2017
Cockrell School Graduate Student Fellowship
University of Texas at Austin Sep 2013
Yang Fuqing and Wang Yangyuan Academician Scholarship
Peking University Sep 2011
Li Yanhong Baidu Scholarship
Peking University Sep 2010

Misc

Contact

var dimensionValue = 'SOME_DIMENSION_VALUE'; ga('set', 'dimension1', dimensionValue);