Hi, I’m Meng Li

I am currently working as a senior research scientist and tech lead in the Facebook On-Device AI group with focus on building efficient neural networks and hardwares for Facebook AR/VR applications. The mission of our group is to develop full-stack solution, fron hardware accelerator architecture to application, to enable energy-efficient neural network processing on the edge.

I received my Ph.D. degree in the Department of Electrical and Computer Engineering, University of Texas at Austin. I worked in UTDA Lab, under the supervision of Prof. David Z. Pan.

Before joining the group, I received my master degree in University of Texas at Austin under the supervision of Prof. Michael Orshansky, and my bachelor degree in Peking University under the supervision of Prof. Ru Huang and Prof. Runsheng Wang.

News

[04/2020] I will serve as in the technical program committee of ICCAD 2020 and the session chair of DAC 2020.
[03/2020] I am promoted to Senior Research Scientist and Tech Lead in Facebook On-Device AI group leading the effort on building efficient neural networks for Facebook AR/VR applications.
[02/2020] Our work with Univeristy of Notre Dame and Georgia Tech on neural network and hardware co-optimization through joint architecture search is accepted by DAC 2020.
[10/2019] Two papers on energy-efficient neural network algorithm and hardware are accepted by NeurIPs EMC2 Workshop. The full papers available on Arxiv.
[05/2019] I receive the Margarida Jacome Outstanding Dissertation Prize from the ECE Department of UT Austin. Cheers!
[03/2019] I receive the EDAA Outstanding Dissertation Award. Cheers!
[11/2018] I will serve in the technical program committee in HOST 2019.
[11/2018] Two papers on hotspot detection are accepted by ASPDAC 2019 and DATE 2019. Cheers!
[09/2018] I joined Facebook working on energy-efficient deep learning acceleration.
[08/2018] I successfully defended my dissertation. Cheers!

Research Interest

Efficient DL on the Edge

Efficient hardware architecture for DL acceleration
Hardware/Network Co-Design and Co-Optimization
Pruning, Quantization, Architecture Search

Hardware-Oriented Security

Physical unclonable function
IC encryption/camouflaging
Split manufacturing

Hardware Reliability

Single event upset
Random Telegraph Noise
Negative Bias Temperature Instability

Backend Design Automation

Global/Detail placement
Power grid sparsification
Design for manufacturability

Working Experience

Senior Research Scientist

Facebook On-Device AI, 09/2018 - Present
Energy-efficient deep learning acceleration

Research Intern

Arm Inc, summer 2017
Mentor: Vikas Chandra, Liangzhen Lai
Privacy-preserving deep learning

Research Intern

Arm Inc, summer 2016
Mentor: Vikas Chandra, Liangzhen Lai
System security evaluation

R&D Intern

Cadence Design Inc, summer 2014
Mentor: Sharad Mehrotra
Fast timing analysis engine

Education

Ph.D.

2016 - 2018
Electrical and Computer Engineering
The University of Texas at Austin

Master of Science

2013 - 2015
Electrical and Computer Engineering
The University of Texas at Austin

Bachelor of Science

2009 - 2013
Microelectronics
Peking University

Honors

Margarida Jacome Outstanding Dissertation Prize - by UT Austin 2019
EDAA Outstanding Dissertation Award - by EDAA 2019
Best Paper Award - by ACM GLSVLSI 2018
First place at ACM Student Research Competition - by ACM 2018
Best Poster (Presentation) Award at ASPDAC Student Research Forum - by ACM SIGDA 2018
Gold Medal at Design Automation Student Research Competition - by ACM SIGDA 2017
Best Paper Award - by HOST 2017
Cockrell School Graduate Student Fellowship - by University of Texas at Austin 2013
Pacemaker to Merit Student - by Peking University 2012
Merit Student - by Peking University 2012
Yang Fuqing and Wang Yangyuan Academician Scholarship - by Peking University 2011
Li Yanhong Baidu Scholarship - by Peking University 2010

Publications

Preprint

[P4] Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
- Preprint
- Dilin Wang, Meng Li, Lemeng Wu, Vikas Chandra and Qiang Liu
- arXiv, 2019
[P3] A Synergistic Framework for Hardware IP Privacy and Integrity Protection
- Preprint
- Meng Li and David Z. Pan
- ACM Student Research Competition Grand Final, 2018 (Gold Metal in Graduate Category)
[P2] Federated Learning with Non-IID Data
- Preprint
- Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin and Vikas Chandra
- arXiv, 2018
[P1] PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training
- Preprint
- Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra and David Z. Pan
- arXiv, 2017

2020

[J12] TimingCamouflage+: Netlist Security Enhancement with Unconventional Timing
- Preprint
- Grace Li Zhang, Bing Li, Meng Li, Bei Yu, David Z. Pan, Michaela Brunner, Georg Sigl and Ulf Schlichtmann
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2020

[C29] Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
- Preprint
- Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi
- IEEE/ACM Design Automation Conference (DAC), San Francisco, CA, July 19-23, 2020

2019

[J11] IP Protection and Supply Chain Security through Logic Obfuscation: A Systematic Overview
- Preprint
- Kaveh Shamsi, Meng Li, Kenneth Plaks, Saverio Fazzari, David Z. Pan, and Yier Jin
- ACM Transactions on Design Automation of Electronic Systems (TODAES), 2019

[C28] Improving Efficiency in Neural Network Acceleration Using Operands Hamming Distance Optimization
- Preprint
- Meng Li*, Yilei Li*, Pierce Chuang, Liangzhen Lai, Vikas Chandra
- Workshop on Energy Efficient Machine Learning and Cognitive Computing, NeurIPS , Vancouver, BC, Canada, 2019
[C27] Energy-Aware Neural Architecture Optimization With Splitting Steepest Descent
- Preprint
- Dilin Wang, Lemeng Wu, Meng Li, Vikas Chandra and Qiang Liu
- Workshop on Energy Efficient Machine Learning and Cognitive Computing, NeurIPS , Vancouver, BC, Canada, 2019
[C26] GAN-SRAF: Sub-Resolution Assist Feature Generation using Conditional Generative Adversarial Networks
- Preprint
- Mohamed Baker Alawieh, Yibo Lin, Meng Li, Zaiwei Zhang, Qixing Huang and David Z. Pan
- IEEE/ACM Design Automation Conference (DAC), Las Vegas, NV, Jun. 3-5, 2019
[C25] KC2: Key-Condition Crunching for Fast Sequential Circuit Obfuscation
- Preprint
- Kaveh Shamsi, Meng Li, David Z. Pan, and Yier Jin
- IEEE/ACM Design, Automation and Test in Europe (DATE), Florence, Italy, Mar. 25-29, 2019
[C24] Litho-GPA: Gaussian Process Assurance for Lithography Hotspot Detection
- Preprint
- Wei Ye, Mohamed Baker Alawieh, Meng Li, Yibo Lin, and David Z. Pan
- IEEE/ACM Design, Automation and Test in Europe (DATE), Florence, Italy, Mar. 25-29, 2019
[C23] Hardware-software Co-design of Slimmed Optical Neural Networks
- Preprint
- Zheng Zhao, Derong Liu, Meng Li, Zhoufeng Ying, Biying Xu, Lu Zhang, Bei Yu, Ray T. Chen, and David Z. Pan
- IEEE/ACM Asia and South Pacific Design Automation Conference (ASPDAC), Tokyo, Japan, Jan. 21-24, 2019
[C22] LithoROC: Lithography Hotspot Detection with Explicit ROC Optimization
- Preprint
- Wei Ye, Yibo Lin, Meng Li, Qiang Liu, and David Z. Pan
- IEEE/ACM Asia and South Pacific Design Automation Conference (ASPDAC), Tokyo, Japan, Jan. 21-24, 2019

2018

[J10] Data Efficient Lithography Modeling with Transfer Learning and Active Data Selection
- Preprint
- Yibo Lin, Meng Li, Yuki Watanabe, Taiki Kimura, Tetsuaki Matsunawa, Shigeki Nojima, and David Z. Pan
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2018
[J9] A Practical Split Manufacturing Framework for Trojan Prevention via Simultaneous Wire Lifting and Cell Insertion
- Preprint
- Meng Li, Bei Yu, Yibo Lin, Xiaoqing Xu, Wuxi Li and David Z. Pan
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2018
[J8] On the Approximation Resiliency of Logic Locking and IC Camouflaging Schemes
- Preprint
- Kaveh Shamsi, Travis Meade, Meng Li, David Z. Pan and Yier Jin
- IEEE Transactions on Information Forensics and Security (TIFS), 2018
[J7] UTPlaceF 2.0: A High-Performance Clock-Aware FPGA Placement Engine
- Preprint
- Wuxi Li, Yibo Lin, Meng Li, Shounak Dhar and David Z. Pan
- ACM Transactions on Design Automation of Electronic Systems (TODAES), 2018
[J6] Provably Secure Camouflaging Strategy for IC Protection
- Preprint
- Meng Li, Kaveh Shamsi, Travis Meade, Zheng Zhao, Bei Yu, Yier Jin and David Z. Pan
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) , 2018

[C21] TimingSAT: Decamouflaging Timing-based Logic Obfuscation
- Preprint
- Meng Li, Kaveh Shamsi, Yier Jin and David Z. Pan
- IEEE International Testing Conference, Phoenix, Az, USA, Oct 28 - Nov 2, 2018
[C20] Cross-Lock: Dense Layout-Level Interconnect Locking using Cross-bar Architectures
- Preprint
- Kaveh Shamsi, Meng Li, David Z. Pan and Yier Jin
- ACM Great Lakes Symposium on VLSI (GLSVLSI), Chicago, IL, USA, May 23-25, 2018
[C19] Power Grid Reduction by Sparse Convex Optimization
- Preprint
- Wei Ye, Meng Li, Kai Zhong, Bei Yu and David Z. Pan
- International Symposium on Physical Design (ISPD) , Monterey, California, USA, Mar. 25-28, 2018
[C18] Data Efficient Lithography Modeling with Residual Neural Network and Transfer Learning
- Preprint
- Yibo Lin, Yuki Watanabe, Taiki Kimura, Tetsuaki Matsunawa, Shigeki Nojima, Meng Li and David Z. Pan
- International Symposium on Physical Design (ISPD) , Monterey, California, USA, Mar. 25-28, 2018
[C17] Layout-Dependent Aging Mitigation for Critical Path Timing
- Preprint
- Che-Lun Hsu, Shaofeng Guo, Yibo Lin, Xiaoqing Xu, Meng Li, Runsheng Wang, Ru Huang and David Z. Pan
- Asia and South Pacific Design Automation Conference (ASPDAC), Jeju Island, Korea, Jan. 22-25, 2018
[C16] A Practical Split Manufacturing Framework for Trojan Prevention via Simultaneous Wire Lifting and Cell Insertion
- Preprint
- Meng Li, Bei Yu, Yibo Lin, Xiaoqing Xu, Wuxi Li and David Z. Pan
- Asia and South Pacific Design Automation Conference (ASPDAC), Jeju Island, Korea, Jan. 22-25, 2018

2017

[J5] Layout Synthesis for Topological Quantum Circuits with 1D and 2D Architectures
- Preprint
- Yibo Lin, Bei Yu, Meng Li and David Z. Pan
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2017
[J4] SD-PUF: Spliced Digital Physical Unclonable Function
- Preprint
- Jin Miao, Meng Li, Subhendu Roy, Yuzhe Ma and Bei Yu
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2017
[J3] Sub-Resolution Assist Feature Generation with Supervised Data Learning
- Preprint
- Xiaoqing Xu, Yibo Lin, Meng Li, Tetsuaki Matsunawa, Shigeki Nojima, Chikaaki Kodama, Toshiya Kotani and David Z. Pan
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2017
[J2] Redundant Local-Loop Insertion for Unidirectional Routing
- Preprint
- Xiaoqing Xu, Yibo Lin, Meng Li, Jiaojiao Ou, Brian Cline and David Z. Pan
- IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2017

[C15] UTPlaceF 3.0: A Parallelization Framework for Modern FPGA Global Placement
- Preprint
- Wuxi Li, Meng Li, Jiajun Wang and David Z. Pan
- IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Irvine, CA, Nov. 13-16, 2017 (invited)
[C14] Cross-level Monte Carlo Framework for System Vulnerability Evaluation against Fault Attack
- Preprint
- Meng Li, Liangzhen Lai, Vikas Chandra and David Z. Pan
- IEEE/ACM Design Automation Conference (DAC), Austin, TX, Jun. 18-22, 2017
[C13] Cyclic Obfuscation for Creating SAT-Unresolvable Circuits
- Preprint
- Kaveh Shamsi, Meng Li, Travis Meade, Zheng Zhao, David Z. Pan and Yier Jin
- ACM Great Lakes Symposium on VLSI (GLSVLSI), Banff, Alberta, Canada, May 10-12, 2017
[C12] Circuit Obfuscation and Oracle-guided Attacks: Who Can Prevail?
- Preprint
- Kaveh Shamsi, Meng Li, Travis Meade, Zheng Zhao, David Z. Pan and Yier Jin
- ACM Great Lakes Symposium on VLSI (GLSVLSI), Banff, Alberta, Canada, May 10-12, 2017 (invited)
[C11] AppSAT: Approximately Deobfuscating Integrated Circuits
- Preprint
- Kaveh Shamsi, Meng Li, Travis Meade, Zheng Zhao, David Z. Pan and Yier Jin
- IEEE International Symposium on Hardware Oriented Security and Trust (HOST), McLean, VA, May 1-4, 2017 (best paper award)

2016

[C10] Provably Secure Camouflaging Strategy for IC Protection
- Preprint
- Meng Li, Kaveh Shamsi, Travis Meade, Zheng Zhao, Bei Yu, Yier Jin and David Z. Pan
- IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Austin, TX, Nov. 7-10, 2016
[C9] LRR-DPUF: Learning Resilient and Reliable Digital Physical Unclonable Function
- Preprint
- Jin Miao, Meng Li, Subhendu Roy and Bei Yu
- IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Austin, TX, Nov. 7-10, 2016
[C8] Proxy-Guided Load Balancing of Graph Processing Workloads on Heterogeneous Clusters
- Preprint
- Shuang Song, Meng Li, Xinnian Zheng, Jee Ho Ryoo, Reena Panda, Michael LeBeane, Andreas Gerstlauer and Lizy K. John
- IEEE International Conference on Parallel Processing (ICPP), Philadelphia, PA, Aug. 16-19, 2016
[C7] A Monte Carlo Simulation Flow for SEU Analysis of Sequential Circuits
- Preprint
- Meng Li, Ye Wang and Michael Orshansky
- IEEE/ACM Design Automation Conference (DAC), Austin, TX, Jun. 5-9, 2016
[C6] Practical Public PUF Enabled by Solving Max-Flow Problem on Chip
- Preprint
- Meng Li, Jin Miao, Kai Zhong and David Z. Pan
- IEEE/ACM Design Automation Conference (DAC), Austin, TX, Jun. 5-9, 2016

2015

[C5] Design Optimization of a Strong PUF Based on Nonlinearity of MOSFET Subthreshold Operation
- Xiaodan Xi, Meng Li, Jaeyoung Park and Michael Orshansky
- SRC Techcon, Austin, TX, Sept. 20-22, 2015
[C4] Novel Power Grid Reduction Method based on L1 Regularization
- Preprint
- Ye Wang, Meng Li, Xinyang Yi, Zhao Song, Michael Orshansky and Constantine Caramanis
- IEEE/ACM Design Automation Conference (DAC), San Francisco, CA, Jun. 7-11, 2015

2014

[C3] An End-to-End SEU Simulation Platform
- Meng Li, Yuan Yi, Derek Chiou and Michael Orshansky
- SRC Techcon, Austin, Tx, Sept. 20-22, 2014

2013

[J1] Characterization of Random Telegraph Noise in Scaled High-k/Metal-Gate MOSFETs with SiO2/HfO2 Gate Dielectrics
- Preprint
- Meng Li, Runsheng Wang, Jibin Zou and Ru Huang
- ECS Transactions, vol. 52, issue 1, pp. 941-946, 2013

[C2] Impact of Cycle-to-Cycle Variation Effects on the Prediction of NBTI Degradation and the Resulted Dynamic Variations in high-k MOSFETs
- Preprint
- Pengpeng Ren, Changze Liu, Runsheng Wang, Meng Li, Yangyuan Wang and Ru Huang
- International Symposium on VLSI Technology, Systems, and Applications (VLSI-TSA), Hsinchu, Taiwan, Apr. 22-24, 2013

2012

[C1] Investigation on the Correlation Between Line-Edge-Roughness (LER) and Line-Width-Roughness (LWR) in Nanoscale CMOS Technology
- Preprint
- Xiaobo Jiang, Meng Li, Runsheng Wang, Jiang Chen and Ru Huang
- International Conference on Solid-State and Integrated Circuit Technology (ICSICT), Xian, Shanxi, Oct.29 - Nov. 1, 2012