Yanqi Zhou

Staff Research Scientist at Google Deepmind

Yanqi Zhou is currently a staff research scientist at Google Deepmind (previously known as Google Brain), Mountain View, working with James Laudon. She pursued her Ph.D. degree at Princeton University, advised by David Wentzlaff. During her Ph.D. study (2011-2017), she also collaborated extensively with Doug Burger and Karin Strauss at Microsoft Research. She obtained her bachelor degree from the University of Michigan (2009-2011), and Shanghai Jiao Tong (2007-2009). Her research interest lies in computer systems and machine learning. More specifically, Yanqi works on scaling large language models with sparsity and adaptive computation, and co-designing future systems with ML.

yanqiz [at] google [dot] com
Google Scholar

Papers

• Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
  Tao Lei, Junwen Bai, Siddhartha Brahma, Joshua Ainslie, Kenton Lee,
  Yanqi Zhou, Nan Du, Vincent Y Zhao, Yuexin Wu, Bo Li, Yu Zhang, Ming-Wei Chang
  In Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023
  NeurIPS
• Learning Large Graph Property Prediction via Graph Segment Training
  Kaidi Cao, Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Dustin Zelle,
  Yanqi Zhou, Charith Mendis, Jure Leskovec, Bryan Perozzi
  In Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023
  NeurIPS
• TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching
  Cheng Fu, Hanxian Huang, Zixuan Jiang, Yun Ni, Lifeng Nai, Gang Wu, Liqun Cheng,
  Yanqi Zhou, Sheng Li, Andrew Li, Jishen Zhao
  In Proceedings of the International Conference on Computer Vision (ICCV), 2023
  ICCV
• Brainformers: Trading Simplicity for Efficiency
  Yanqi Zhou, Nan Du, Yanping Huang, Daiyi Peng, Chang Lan, Da Huang, Siamak Shakeri,
  David So, Andrew M. Dai, Yifeng Lu, Zhifeng Chen, Quoc V Le, Claire Cui, James Laudon, Jeff Dean
  In Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
  ICML
• Lifelong Language Pretraining with Distribution-Specialized Experts
  Wuyang Chen, Yanqi Zhou, Nan Du, Yanping Huang, James Laudon, Zhifeng Chen, Claire Cui
  In Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
  ICML
• GiPH: Generalizable Placement Learning for Adaptive Heterogeneous Computing
  Yi Hu, Chaoran Zhang, Edward Andert, Harshul Singh, Aviral Shrivastava, James Laudon,
  Yanqi Zhou, Bob Iannucci, Carlee Joe-Wong
  In Proceedings of the 40th International Conference on Machine Learning (MLSys), 2023
  MLSys
• Mixture-of-Experts with Expert Choice Routing
  Yanqi Zhou, Tao Lei, Hanxiao Liu, Nan Du, Yanping Huang, Vincent Zhao, Andrew Dai,
  Zhifeng Chen, Quoc Le, James Laudon
  In Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022
  arxiv
• Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search
  Thanh Vu, Yanqi Zhou, Chunfeng Wen, Yueqi Li, Jan-Michael Frahm
  In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
  arxiv
• A Transferable Approach for Partitioning Machine Learning Models on Multi-Chip-Modules
  Xinfeng Xie, Prakash Prabhu, Ulysse Beaugnon, Phitchaya Phothilimthana, Sudip Roy,
  Azalia Mirhoseini, Eugene Brevdo, James Laudon, Yanqi Zhou
  In Proceedings of the 4th MLSys Conference (MLSys), 2022
  MLSys
• Towards the Co-design of Neural Networks and Accelerators
  Yanqi Zhou, Xuanyi Dong, Tianjian Meng, Mingxing Tan, Berkin Akin, Daiyi Peng,
  Amir Yazdanbakhsh, Da Huang, Ravi Narayanaswami, James Laudon
  In Proceedings of the 4th MLSys Conference (MLSys), 2022
  MLSys
• A Learned Performance Model for Tensor Processing Units
  Samuel J. Kaufman, Phitchaya Mangpo Phothilimthana, Yanqi Zhou, Charith Mendis,
  Sudip Roy, Amit Sabne, Mike Burrows
  In Proceedings of the 4th MLSys Conference (MLSys), 2021
  arxiv
• Transferable Graph Optimizers for ML Compilers
  Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Wong, Peter C. Ma, Qiumin Xu,
  Hanxiao Liu, Mangpo Phitchaya Phothilimtha, Shen Wang, Anna Goldie, Azalia Mirhoseini, James Laudon
  In Thirty-fourth Conference on Neural Informationn Processing Systems (NeurIPS), 2020
  arxiv
• Omnidirectional Depth Extension Networks
  Xinjing Cheng, Peng Wang, Yanqi Zhou, Chenye Guan, Ruigang Yang
  ICRA , 2020
  
• GDP: Generalized Device Placement for Dataflow Graphs
  Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Wong, Peter C. Ma, Qiumin Xu,
  Ming Zhong, Hanxiao Liu, Anna Goldie, Azalia Mirhoseini, James Laudon
  arxiv
Exploring the limits of transfer learning with a unified text-to-text transformer
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena,
Yanqi Zhou, Wei Li, Peter J Liu
JMLR , 2020
paper
• Swift Machine Learning Model Serving Scheduling: A Region Based Reinforcement Learning Approach
  Heyang Qin, Syed Zawad, Yanqi Zhou, Lei Yang, Dongfang Zhao, Feng Yan
  In Proceedings of the International Conference for High Performance Computing,
  Networking, Storage and Analysis (SC), 2019
  paper
• EPNAS: Efficient Progressive Neural Architecture Search
  Yanqi Zhou, Peng Wang, Sercan Arik, Haonan Yu, Syed Zawad, Feng Yan, Greg Diamos
  In British Machine Vision Conference (BMVC), 2019
  arxiv
• Neural Voice Cloning With a Few Samples
  Sercan Arik, Jitong Chen, Kainan Peng, Wei Ping, Yanqi Zhou
  In Thirty-second Conference on Neural Information Processing Systems (NeurIPS), 2018
  arxiv
• Deep Voice 2: Multi-Speaker Neural Text-to-Speech
  Sercan Arik, Gregory Diamos, Andrew Gibiansky, John Miller, Kainan Peng,
  Wei Ping, Jonathan Raiman, Yanqi Zhou
  In Thirty-first Conference on Neural Information Processing Systems (NeurIPS), 2017
  arxiv
• Power and Energy Characterization of an Open Source 25-Core Manycore Processor
  Michael McKeown, Alexey Lavrov, Mohammad Shahrad, Paul J. Jackson, Yaosheng Fu,
  Jonathan Balkind, Tri M. Nguyen, Katie Lim, Yanqi Zhou, David Wentzlaff
  In IEEE International Symposium on High Performance Computer Architecture (HPCA), 2018
  paper
• Piton: A Manycore Processor for Multitenant Clouds
  Michael McKeown, Yaosheng Fu, Tri Nguyen, Yanqi Zhou, Jonathan Balkind, Alexey Lavrov,
  Mohammad Shahrad, Samuel Payne, David Wentzlaff
  IEEE Micro, 2017
  paper
• Atomic In-place Updates for Non-volatile Main Memories with Kamino-Tx
  Amirsaman Memaripour, Anirudh Badam, Amar Phanishayee, Yanqi Zhou, Ram Alagappan,
  Karin Strauss, and Steven Swanson
  In Proceedings of the Twelfth European Conference on Computer Systems (EuroSys), 2017
  paper
• Camouflage: Memory traffic shaping to mitigate timing attacks
  Yanqi Zhou, Sameer Wagh, Prateek Mittal, David Wentzlaff
  In IEEE International Symposium on High Performance Computer Architecture (HPCA), 2017
  paper
• MITTS: Memory inter-arrival time traffic shaping
  Yanqi Zhou, David Wentzlaff
  In ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), 2016
  paper
• CASH: Supporting IaaS customers with a sub-core configurable architecture
  Yanqi Zhou, Henry Hoffmann, David Wentzlaff
  In ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), 2016
  paper
  
• Piton: A 25-core Academic Manycore Research Processor
  Michael McKeown, Yaosheng Fu, Tri M Nguyen, Yanqi Zhou, Jonathan Balkind,
  Alexey Lavrov, Mohammad Shahrad, Samuel Payne, David Wentzlaff
  In Hot Chips Symposium (HotChips), 2016
  slides
  
• Piton: A 25-core Academic Manycore Research Processor
  Jonathan Balkind, Michael McKeown, Yaosheng Fu, Tri Nguyen, Yanqi Zhou, Alexey Lavrov,
  Mohammad Shahrad, Adi Fuchs, Samuel Payne, Xiaohua Liang, Matthew Matl, David Wentzlaff
  In Proceedings of the Twenty-First International Conference on Architectural Support
  for Programming Languages and Operating Systems (ASPLOS), 2016
  paper
  
• The sharing architecture: sub-core configurability for IaaS clouds
  Yanqi Zhou, David Wentzlaff
  In Proceedings of the 19th international conference on Architectural support
  for programming languages and operating systems (ASPLOS), 2014
  paper
  

Awards and Honors

• Rising Stars, Carnegie Mellon University, 2016
• Wu Fellowship, Princeton University, 2016
• Microsoft Ph.D. Fellowship, Microsoft, 2014-2015
• James B. Angell Scholar, University of Michigan, 2011
• Dean's List and University Honors (Three times), University of Michigan, 2009-2011

Working Experience

• Research Scientist, Google Brain, 2019 -
• Research Scientist, Baidu SVAIL, 2017 - 2019
• Research Assitant, Princeton University, 2011 - 2017
• Intern, Miscrosoft Research Redmond, Summer 2014 and 2015

Services

• Review for NeurIPS, 2019, 2020
• Review for ICML, 2019, 2020
• Review for IEEE Transactions on Computers, IEEE Embedded System Letters,
  Transactions on Design Automation of Electronic Systems, 2016