Liangzhen Lai

50 papers A* 7A 5Misc 4Journal 26Unranked 8
YearRankTypeTitle / Venue / Authors
2025 — conf
Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions.
NAACL (Industry Track)
Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra
2024 Misc conf
Folding Attention: Memory and Power Optimization for On-Device Transformer-Based Streaming Speech Recognition.
ICASSP
Yang Li, Liangzhen Lai, Yuan Shangguan, Forrest N. Iandola, Zhaoheng Ni, Ernie Chang, Yangyang Shi, Vikas Chandra
2024 — conf
GPU-based Private Information Retrieval for On-Device Machine Learning Inference.
ASPLOS (1)
Maximilian Lam, Jeff Johnson, Wenjie Xiong, Kiwan Maeng, Udit Gupta, Yang Li, Liangzhen Lai, Ilias Leontiadis, Minsoo Rhu, Hsien-Hsin S. Lee, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks, G. Edward Suh
2024 — conf
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.
ACL (1)
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed A. Aly, Beidi Chen, Carole-Jean Wu
2024 J jnl
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.
CoRR
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed A. Aly, Beidi Chen, Carole-Jean Wu
2024 A* conf
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.
ICML
Zechun Liu, Changsheng Zhao, Forrest N. Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra
2024 J jnl
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.
CoRR
Zechun Liu, Changsheng Zhao, Forrest N. Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra
2024 J jnl
Not All Weights Are Created Equal: Enhancing Energy Efficiency in On-Device Streaming Speech Recognition.
CoRR
Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra
2024 J jnl
PipeOrgan: Efficient Inter-operation Pipelining with Flexible Spatial Organization and Interconnects.
CoRR
Raveesh Garg, Hyoukjun Kwon, Eric Qin, Yu-Hsin Chen, Tushar Krishna, Liangzhen Lai
2023 — conf
DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads.
ASPLOS (4)
Seah Kim, Hyoukjun Kwon, Jinook Song, Jihyuck Jo, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra
2023 A* conf
Efficient Non-Linear Adder for Stochastic Computing with Approximate Spatial-Temporal Sorting Network.
DAC
Yixuan Hu, Tengyu Zhang, Meng Li, Renjie Wei, Liangzhen Lai, Yuan Wang, Runsheng Wang, Ru Huang
2023 J jnl
Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition.
CoRR
Yang Li, Liangzhen Lai, Yuan Shangguan, Forrest N. Iandola, Ernie Chang, Yangyang Shi, Vikas Chandra
2023 J jnl
GPU-based Private Information Retrieval for On-Device Machine Learning Inference.
CoRR
Maximilian Lam, Jeff Johnson, Wenjie Xiong, Kiwan Maeng, Udit Gupta, Yang Li, Liangzhen Lai, Ilias Leontiadis, Minsoo Rhu, Hsien-Hsin S. Lee, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks, G. Edward Suh
2023 — conf
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse.
MLSys
Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby R. Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi
2022 A* conf
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation.
CVPR
Jiaqi Gu, Hyoukjun Kwon, Dilin Wang, Wei Ye, Meng Li, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra, David Z. Pan
2022 J jnl
SDRM3: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads.
CoRR
Seah Kim, Hyoukjun Kwon, Jinook Song, Jihyuck Jo, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra
2022 J jnl
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse.
CoRR
Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby R. Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi
2021 A* conf
Heterogeneous Dataflow Accelerators for Multi-DNN Workloads.
HPCA
Hyoukjun Kwon, Liangzhen Lai, Michael Pellauer, Tushar Krishna, Yu-Hsin Chen, Vikas Chandra
2021 J jnl
Low-Rank+Sparse Tensor Compression for Neural Networks.
CoRR
Cole Hawkins, Haichuan Yang, Meng Li, Liangzhen Lai, Vikas Chandra
2021 J jnl
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation.
CoRR
Jiaqi Gu, Hyoukjun Kwon, Dilin Wang, Wei Ye, Meng Li, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra, David Z. Pan
2020 A* conf
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks.
DAC
Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi
2020 J jnl
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks.
CoRR
Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi
2020 J jnl
Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization.
CoRR
Meng Li, Yilei Li, Pierce Chuang, Liangzhen Lai, Vikas Chandra
2019 J jnl
HERALD: Optimizing Heterogeneous DNN Accelerators for Edge Devices.
CoRR
Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra
2019 Misc conf
SenseHAR: a robust virtual activity sensor for smartphones and wearables.
SenSys
Jeya Vikranth Jeyakumar, Liangzhen Lai, Naveen Suda, Mani B. Srivastava
2018 A* conf
Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network.
ISCA
Hardik Sharma, Jongse Park, Naveen Suda, Liangzhen Lai, Benson Chau, Vikas Chandra, Hadi Esmaeilzadeh
2018 J jnl
CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs.
CoRR
Liangzhen Lai, Naveen Suda, Vikas Chandra
2018 A conf
Enabling deep learning at the IoT edge.
ICCAD
Liangzhen Lai, Naveen Suda
2018 J jnl
Federated Learning with Non-IID Data.
CoRR
Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, Vikas Chandra
2018 J jnl
Not All Ops Are Created Equal!
CoRR
Liangzhen Lai, Naveen Suda, Vikas Chandra
2018 J jnl
Rethinking Machine Learning Development and Deployment for Edge Devices.
CoRR
Liangzhen Lai, Naveen Suda
2017 J jnl
Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks.
CoRR
Hardik Sharma, Jongse Park, Naveen Suda, Liangzhen Lai, Benson Chau, Joon Kyung Kim, Vikas Chandra, Hadi Esmaeilzadeh
2017 A* conf
Cross-level Monte Carlo Framework for System Vulnerability Evaluation against Fault Attack.
DAC
Meng Li, Liangzhen Lai, Vikas Chandra, David Z. Pan
2017 J jnl
Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations.
CoRR
Liangzhen Lai, Naveen Suda, Vikas Chandra
2017 A conf
Exploiting data-dependence and Flip-Flop asymmetry for zero-overhead system soft error mitigation.
DATE
Vikas Chandra, Liangzhen Lai
2017 J jnl
Hello Edge: Keyword Spotting on Microcontrollers.
CoRR
Yundong Zhang, Naveen Suda, Liangzhen Lai, Vikas Chandra
2017 J jnl
PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training with A Fine-Grained Privacy Control.
CoRR
Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Z. Pan
2017 J jnl
System-Level Dynamic Variation Margining in Presence of Monitoring and Actuation.
IEEE Embed. Syst. Lett.
Liangzhen Lai, Puneet Gupta
2016 — conf
Hardware Reliability margining for the dark silicon era.
ASP-DAC
Liangzhen Lai, Puneet Gupta
2016 A conf
Multi-story power distribution networks for GPUs.
DATE
Qixiang Zhang, Liangzhen Lai, Mark Gottscho, Puneet Gupta
2016 A conf
Resiliency in dynamically power managed designs.
ICCAD
Liangzhen Lai, Vikas Chandra, Rob Aitken
2015 Misc conf
Evaluating and exploiting impacts of dynamic power management schemes on system reliability.
CASES
Liangzhen Lai, Vikas Chandra, Puneet Gupta
2015 J jnl
NSF expedition on variability-aware software: Recent results and contributions.
it Inf. Technol.
Lucas Francisco Wanner, Liangzhen Lai, Abbas Rahimi, Mark Gottscho, Pietro Mercati, Chu-Hsiang Huang, Frederic Sala, Yuvraj Agarwal, Lara Dolecek, Nikil D. Dutt, Puneet Gupta, Rajesh K. Gupta, Ranjit Jhala, Rakesh Kumar, Sorin Lerner, Subhasish Mitra, Alexandru Nicolau, Tajana Simunic Rosing, Mani B. Srivastava, Steven Swanson, Dennis Sylvester, Yuanyuan Zhou
2014 — conf
Accurate and inexpensive performance monitoring for variability-aware systems.
ASP-DAC
Liangzhen Lai, Puneet Gupta
2014 J jnl
BTI-Gater: An Aging-Resilient Clock Gating Methodology.
IEEE J. Emerg. Sel. Topics Circuits Syst.
Liangzhen Lai, Vikas Chandra, Robert C. Aitken, Puneet Gupta
2014 J jnl
SlackProbe: A Flexible and Efficient In Situ Timing Slack Monitoring Methodology.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Liangzhen Lai, Vikas Chandra, Robert C. Aitken, Puneet Gupta
2014 J jnl
Synthesis and Analysis of Design-Dependent Ring Oscillator (DDRO) Performance Monitors.
IEEE Trans. Very Large Scale Integr. Syst.
Tuck-Boon Chan, Puneet Gupta, Andrew B. Kahng, Liangzhen Lai
2013 A conf
SlackProbe: a low overhead in situ on-line timing slack monitoring methodology.
DATE
Liangzhen Lai, Vikas Chandra, Robert C. Aitken, Puneet Gupta
2013 Misc conf
VarEMU: An emulation testbed for variability-aware software.
CODES+ISSS
Lucas Francisco Wanner, Salma Elmalaki, Liangzhen Lai, Puneet Gupta, Mani B. Srivastava
2012 — conf
DDRO: A novel performance monitoring methodology based on design-dependent ring oscillators.
ISQED
Tuck-Boon Chan, Puneet Gupta, Andrew B. Kahng, Liangzhen Lai