VS
Vivienne Sze
cs.CVcs.ARcs.ROcs.LGcs.DCcs.ETeess.IVSaccadesSmartphonecs.AI
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
46 papers in the corpus · 2016–2026AccelForge: Comprehensive Modeling and Co-Design Framework for AI Accelerators2609.11906v1 · Tanner Andrulis, Michael Gilbert, Vivienne Sze et al.2026 · 0 citationsarXiv
iPad Eye Tracking Reproduces Clinical Grade Oculomotor Differences in Parkinson's Disease.42156978 · Koerner, Jamie, Zou, Erin, Karl, Jessica A et al.2026 · 0 citationsNPJ digital medicine. 2026;9(1)
G$^2$SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstruction2607.14470v1 · Dasong Gao, Vivienne Sze, Sertac Karaman2026 · 0 citationsarXiv
UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians2605.23098v1 · Soumya Sudhakar, Sertac Karaman, Vivienne Sze2026 · 0 citationsarXiv
Fast and Fusiest: An Optimal Fusion-Aware Mapper for Accelerator Design2602.15166v2 · Tanner Andrulis, Michael Gilbert, Vivienne Sze et al.2026 · 0 citationsarXiv
The Turbo-Charged Mapper: Fast and Optimal Mapping for Energy-efficient and Low-latency Accelerator Design2602.15172v2 · Michael Gilbert, Tanner Andrulis, Vivienne Sze et al.2026 · 0 citationsarXiv
Gleanmer: A 6 mW SoC for Real-Time 3D Gaussian Occupancy Mapping2603.29005v1 · Zih-Sing Fu, Peter Zhi Xuan Li, Sertac Karaman et al.2026 · 0 citationsarXiv
Towards scalable screening for the early detection of Parkinson's disease: validation of an iPad-based eye movement assessment system against a clinical-grade eye tracker.40781252 · Koerner, Jamie, Zou, Erin, Karl, Jessica A et al.2025 · 7 citationsNPJ Parkinson's disease. 2025;11(1):233
DecTrain: Deciding When to Train a Monocular Depth DNN Online2410.02980v2 · Zih-Sing Fu, Soumya Sudhakar, Sertac Karaman et al.2024 · 1 citationarXiv
GEVO: Memory-Efficient Monocular Visual Odometry Using Gaussians2409.09295v2 · Dasong Gao, Peter Zhi Xuan Li, Vivienne Sze et al.2024 · 1 citationarXiv
CiMLoop: A Flexible, Accurate, and Fast Compute-In-Memory Modeling Tool2405.07259v2 · Tanner Andrulis, Joel S. Emer, Vivienne Sze2024 · 30 citationsISPASS 2024 pp. 10-23
Architecture-Level Modeling of Photonic Deep Neural Network Accelerators2405.07266v2 · Tanner Andrulis, Gohar Irfan Chaudhry, Vinith M. Suriyakumar et al.2024 · 5 citationsISPASS 2024 pp. 307-309
LoopTree: Exploring the Fused-layer Dataflow Accelerator Design Space2409.13625v4 · Michael Gilbert, Yannan Nellie Wu, Joel S. Emer et al.2024 · 6 citationsarXiv
Tailors: Accelerating Sparse Tensor Algebra by Overbooking Buffer Capacity2310.00192v2 · Zi Yu Xue, Yannan Nellie Wu, Joel S. Emer et al.2023 · 11 citations56th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO '23), 2023
Modeling Analog-Digital-Converter Energy and Area for Compute-In-Memory Accelerator Design2404.06553v2 · Tanner Andrulis, Ruicong Chen, Hae-Seung Lee et al.2024 · 3 citationsarXiv
GMMap: Memory-Efficient Continuous Occupancy Map Using Gaussian Mixture Model2306.03740v3 · Peter Zhi Xuan Li, Sertac Karaman, Vivienne Sze2023 · 15 citationsIEEE Transactions on Robotics 40 (2024) 1339-1355
Gemino: Practical and Robust Neural Compression for Video Conferencing2209.10507v4 · Vibhaalakshmi Sivaraman, Pantea Karimi, Vedantha Venkatapathy et al.2022 · 3 citationsUSENIX NSDI 2024
HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity2305.12718v2 · Yannan Nellie Wu, Po-An Tsai, Saurav Muralidharan et al.2023 · 28 citationsarXiv
RAELLA: Reforming the Arithmetic for Efficient, Low-Resolution, and Low-Loss Analog PIM: No Retraining Required!2304.07935v1 · Tanner Andrulis, Joel S. Emer, Vivienne Sze2023 · 45 citationsarXiv
Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling2205.05826v3 · Yannan Nellie Wu, Po-An Tsai, Angshuman Parashar et al.2022 · 78 citationsarXiv
Efficient Computation of Map-scale Continuous Mutual Information on Chip in Real Time2210.03623v1 · Keshav Gupta, Peter Zhi Xuan Li, Sertac Karaman et al.2022 · 4 citationsarXiv
Developing a Series of AI Challenges for the United States Department of the Air Force2207.07033v1 · Vijay Gadepally, Gregory Angelides, Andrei Barbu et al.2022 · 4 citationsarXiv
App-Based Saccade Latency and Directional Error Determination Across the Adult Age Spectrum.34529556 · Lai, Hsin-Yu, Saavedra-Pena, Gladynel, Sodini, Charles et al.2022 · 11 citationsIEEE transactions on bio-medical engineering. 2022;69(2):1029-1039
Searching for Efficient Multi-Stage Vision Transformers2109.00642v1 · Yi-Lun Liao, Sertac Karaman, Vivienne Sze2021 · 12 citationsarXiv
NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization2104.00031v1 · Tien-Ju Yang, Yi-Lun Liao, Vivienne Sze2021 · 32 citationsarXiv
Measuring Saccade Latency Using Smartphone Cameras.31056528 · Lai, Hsin-Yu, Saavedra-Pena, Gladynel, Sodini, Charles G et al.2021 · 35 citationsIEEE journal of biomedical and health informatics. 2020;24(3):885-897
Freely scalable and reconfigurable optical hardware for deep learning.33542343 · Bernstein, Liane, Sludds, Alexander, Hamerly, Ryan et al.2021 · 75 citationsScientific reports. 2021;11(1):3144
App-based saccade latency and error determination across the adult age spectrum2012.09723v1 · Hsin-Yu Lai, Gladynel Saavedra-Pena, Charles G. Sodini et al.2020 · 0 citationsarXiv
Freely scalable and reconfigurable optical hardware for deep learning2006.13926v1 · Liane Bernstein, Alexander Sludds, Ryan Hamerly (1 et al.2020 · 75 citationsarXiv
Depth Map Estimation of Dynamic Scenes Using Prior Depth Information2002.00297v1 · James Noraky, Vivienne Sze2020 · 1 citationarXiv
Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators1912.12167v1 · Tien-Ju Yang, Vivienne Sze2019 · 52 citationsarXiv
MLSys: The New Frontier of Machine Learning Systems1904.03257v3 · Alexander Ratner, Dan Alistarh, Gustavo Alonso et al.2019 · 20 citationsarXivon Valency
Determination of Saccade Latency Distributions using Video Recordings from Consumer-grade Devices.30440548 · Saavedra-Pena, Gladynel, Lai, Hsin-Yu, Sze, Vivienne et al.2019 · 6 citationsAnnual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. 2018;2018:953-956
Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices1807.07928v2 · Yu-Hsin Chen, Tien-Ju Yang, Joel Emer et al.2018 · 1,124 citationsarXiv
FSMI: Fast computation of Shannon Mutual Information for information-theoretic mapping1905.02238v1 · Zhengdong Zhang, Trevor Henderson, Sertac Karaman et al.2019 · 38 citationsarXiv
Low Power Depth Estimation of Rigid Objects for Time-of-Flight Imaging1810.01930v2 · James Noraky, Vivienne Sze2018 · 15 citationsarXiv
DeeperLab: Single-Shot Image Parser1902.05093v2 · Tien-Ju Yang, Maxwell D. Collins, Yukun Zhu et al.2019 · 161 citationsarXiv
FastDepth: Fast Monocular Depth Estimation on Embedded Systems1903.03273v1 · Diana Wofk, Fangchang Ma, Tien-Ju Yang et al.2019 · 392 citationsarXiv
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications1804.03230v2 · Tien-Ju Yang, Andrew Howard, Bo Chen et al.2018 · 598 citationsarXiv
Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones1809.05780v1 · Amr Suleiman, Zhengdong Zhang, Luca Carlone et al.2018 · 3 citationsarXiv
Hardware for Machine Learning: Challenges and Opportunities1612.07625v5 · Vivienne Sze, Yu-Hsin Chen, Joel Emer et al.2016 · 190 citationsarXiv
FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos1603.08968v2 · Zhengdong Zhang, Vivienne Sze2016 · 42 citationsarXiv
Efficient Processing of Deep Neural Networks: A Tutorial and Survey1703.09039v2 · Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang et al.2017 · 4,287 citationsarXiv
Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning1611.05128v4 · Tien-Ju Yang, Yu-Hsin Chen, Vivienne Sze2016 · 772 citationsarXiv
Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision1703.05853v1 · Amr Suleiman, Yu-Hsin Chen, Joel Emer et al.2017 · 60 citationsarXiv
A 58.6mW Real-Time Programmable Object Detector with Multi-Scale Multi-Object Support Using Deformable Parts Model on 1920x1080 Video at 30fps1607.08635v1 · Amr Suleiman, Zhengdong Zhang, Vivienne Sze2016 · 0 citationsarXiv
Career total: 166 works. 46 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.