Sotabase

Career

· Professor of the Graduate School, University of California, Berkeley1998–
· Chief Technology Officer (CTO) and Senior Vice-President of Research, Synopsys1991–1998
· Chief Technical Officer and Senior Vice-President of Research, Synopsys, Inc.1991–1998
· Member of Technical Staff / Researcher, AT&T Bell Laboratories1984–1991
· PhD in Computer Science, Indiana University Bloomington1979–1984
· B.S., Mathematics, Maharishi International University1974–1978
· B.S., Mathematics, Maharishi University of Management1974–1978
· Co-Director, Berkeley Deep Drive (BDD)

Publications (491)

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size
arXiv.org · 2016
8,190
cited
The Landscape of Parallel Computing Research: A View from Berkeley
2006
2,450
cited
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Computer Vision and Pattern Recognition · 2018
1,394
cited
A Survey of Quantization Methods for Efficient Neural Network Inference
Low-Power Computer Vision · 2021
1,390
cited
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
International Conference on Learning Representations · 2019
1,119
cited
System-level design: orthogonalization of concerns andplatform-based design
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. · 2000
927
cited
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
IEEE International Conference on Robotics and Automation · 2017
889
cited
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
IEEE International Conference on Robotics and Automation · 2018
688
cited
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
arXiv.org · 2020
680
cited
- LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE
2016
647
cited
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
AAAI Conference on Artificial Intelligence · 2019
636
cited
Aligning Large Multimodal Models with Factually Augmented RLHF
Annual Meeting of the Association for Computational Linguistics · 2023
609
cited
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
IEEE International Conference on Computer Vision · 2019
607
cited
Estimation of average switching activity in combinational and sequential circuits
[1992] Proceedings 29th ACM/IEEE Design Automation Conference · 1992
542
cited
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2016
530
cited
Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow
European Conference on Computer Vision · 2010
522
cited
How Much Can CLIP Benefit Vision-and-Language Tasks?
International Conference on Learning Representations · 2021
476
cited
ImageNet Training in Minutes
International Conference on Parallel Processing · 2017
464
cited
ZeroQ: A Novel Zero Shot Quantization Framework
Computer Vision and Pattern Recognition · 2020
462
cited
Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data
IEEE International Conference on Computer Vision · 2019
448
cited
Sotabase