Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Joseph E. Gonzalez

Joseph E. Gonzalez

Accelerating Quadratic Optimization with Reinforcement Learning


Jul 22, 2021
Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato, Goran Banjac, Michael Luo, Francesco Borrelli, Joseph E. Gonzalez, Ion Stoica, Ken Goldberg

Figure 1 for Accelerating Quadratic Optimization with Reinforcement Learning
Figure 2 for Accelerating Quadratic Optimization with Reinforcement Learning
Figure 3 for Accelerating Quadratic Optimization with Reinforcement Learning
Figure 4 for Accelerating Quadratic Optimization with Reinforcement Learning
* 25 pages, 7 figures. Code available at https://github.com/berkeleyautomation/rlqp 
  Access Paper or Ask Questions

Learning Space Partitions for Path Planning


Jul 14, 2021
Kevin Yang, Tianjun Zhang, Chris Cummins, Brandon Cui, Benoit Steiner, Linnan Wang, Joseph E. Gonzalez, Dan Klein, Yuandong Tian

Figure 1 for Learning Space Partitions for Path Planning
Figure 2 for Learning Space Partitions for Path Planning
Figure 3 for Learning Space Partitions for Path Planning
Figure 4 for Learning Space Partitions for Path Planning

  Access Paper or Ask Questions

LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks


Jul 10, 2021
Albert Wilcox, Ashwin Balakrishna, Brijen Thananjeyan, Joseph E. Gonzalez, Ken Goldberg

Figure 1 for LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks
Figure 2 for LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks
Figure 3 for LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks
Figure 4 for LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks
* Preprint, Under Review. First two authors contributed equally 
  Access Paper or Ask Questions

Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies


Jun 29, 2021
Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Jeffrey Ichnowski, Ellen Novoseller, Minho Hwang, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

Figure 1 for Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies
Figure 2 for Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies
Figure 3 for Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies
Figure 4 for Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

  Access Paper or Ask Questions

CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks


Jun 14, 2021
Robert Avram, Jeffrey E. Olgin, Alvin Wan, Zeeshan Ahmed, Louis Verreault-Julien, Sean Abreau, Derek Wan, Joseph E. Gonzalez, Derek Y. So, Krishan Soni, Geoffrey H. Tison

Figure 1 for CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
Figure 2 for CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
Figure 3 for CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
Figure 4 for CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
* 62 pages, 3 main figures, 2 main tables 
  Access Paper or Ask Questions

PAC Best Arm Identification Under a Deadline


Jun 08, 2021
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica, Michael I. Jordan, Ken Goldberg, Joseph E. Gonzalez

Figure 1 for PAC Best Arm Identification Under a Deadline
Figure 2 for PAC Best Arm Identification Under a Deadline
* In submission 
  Access Paper or Ask Questions

Disentangling Dense Multi-Cable Knots


Jun 04, 2021
Vainavi Viswanath, Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Ellen Novoseller, Jeffrey Ichnowski, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

Figure 1 for Disentangling Dense Multi-Cable Knots
Figure 2 for Disentangling Dense Multi-Cable Knots
Figure 3 for Disentangling Dense Multi-Cable Knots
Figure 4 for Disentangling Dense Multi-Cable Knots
* First three authors contributed equally 
  Access Paper or Ask Questions

Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines


Jun 02, 2021
Matthew A. Wright, Joseph E. Gonzalez

Figure 1 for Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines
Figure 2 for Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines
* Work in progress, comments welcome 
  Access Paper or Ask Questions

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training


Apr 29, 2021
Jianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, Ion Stoica, Michael W. Mahoney, Joseph E. Gonzalez

Figure 1 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Figure 2 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Figure 3 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Figure 4 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

  Access Paper or Ask Questions

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models


Apr 21, 2021
Nicholas Rhinehart, Jeff He, Charles Packer, Matthew A. Wright, Rowan McAllister, Joseph E. Gonzalez, Sergey Levine

Figure 1 for Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
Figure 2 for Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
Figure 3 for Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
Figure 4 for Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
* To be published at ICRA 2021. Project page: https://sites.google.com/view/contingency-planning 
  Access Paper or Ask Questions

Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation


Apr 18, 2021
Ruizhe Cheng, Bichen Wu, Peizhao Zhang, Peter Vajda, Joseph E. Gonzalez

Figure 1 for Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
Figure 2 for Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
Figure 3 for Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
* 4 pages, 1 figure 
  Access Paper or Ask Questions

Robust Object Detection via Instance-Level Temporal Cycle Confusion


Apr 16, 2021
Xin Wang, Thomas E. Huang, Benlin Liu, Fisher Yu, Xiaolong Wang, Joseph E. Gonzalez, Trevor Darrell

Figure 1 for Robust Object Detection via Instance-Level Temporal Cycle Confusion
Figure 2 for Robust Object Detection via Instance-Level Temporal Cycle Confusion
Figure 3 for Robust Object Detection via Instance-Level Temporal Cycle Confusion
Figure 4 for Robust Object Detection via Instance-Level Temporal Cycle Confusion

  Access Paper or Ask Questions

Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles


Apr 16, 2021
Ionel Gog, Sukrit Kalra, Peter Schafhalter, Matthew A. Wright, Joseph E. Gonzalez, Ion Stoica

Figure 1 for Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles
Figure 2 for Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles
Figure 3 for Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles
Figure 4 for Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles
* ICRA 2021; 8 pages, 4 figures, 1 table 
  Access Paper or Ask Questions

BeBold: Exploration Beyond the Boundary of Explored Regions


Dec 15, 2020
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian

Figure 1 for BeBold: Exploration Beyond the Boundary of Explored Regions
Figure 2 for BeBold: Exploration Beyond the Boundary of Explored Regions
Figure 3 for BeBold: Exploration Beyond the Boundary of Explored Regions
Figure 4 for BeBold: Exploration Beyond the Boundary of Explored Regions

  Access Paper or Ask Questions

Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation


Nov 12, 2020
Samuel Paradis, Minho Hwang, Brijen Thananjeyan, Jeffrey Ichnowski, Daniel Seita, Danyal Fer, Thomas Low, Joseph E. Gonzalez, Ken Goldberg

Figure 1 for Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation
Figure 2 for Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation
Figure 3 for Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation
Figure 4 for Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation
* 6 pages, 5 figures, 4 tables, submitted to ICRA 2021, supplementary material at https://tinyurl.com/ivs-icra 
  Access Paper or Ask Questions

Untangling Dense Knots by Learning Task-Relevant Keypoints


Nov 10, 2020
Jennifer Grannen, Priya Sundaresan, Brijen Thananjeyan, Jeffrey Ichnowski, Ashwin Balakrishna, Minho Hwang, Vainavi Viswanath, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

Figure 1 for Untangling Dense Knots by Learning Task-Relevant Keypoints
Figure 2 for Untangling Dense Knots by Learning Task-Relevant Keypoints
Figure 3 for Untangling Dense Knots by Learning Task-Relevant Keypoints
Figure 4 for Untangling Dense Knots by Learning Task-Relevant Keypoints
* 4th Conference on Robot Learning (CoRL 2020) 
 * Conference on Robot Learning (CoRL) 2020 Oral. First two authors contributed equally 
  Access Paper or Ask Questions

Resource Allocation in Multi-armed Bandit Exploration: Overcoming Nonlinear Scaling with Adaptive Parallelism


Oct 31, 2020
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica, Michael I. Jordan, Ken Goldberg, Joseph E. Gonzalez

Figure 1 for Resource Allocation in Multi-armed Bandit Exploration: Overcoming Nonlinear Scaling with Adaptive Parallelism
Figure 2 for Resource Allocation in Multi-armed Bandit Exploration: Overcoming Nonlinear Scaling with Adaptive Parallelism
Figure 3 for Resource Allocation in Multi-armed Bandit Exploration: Overcoming Nonlinear Scaling with Adaptive Parallelism
* Preprint. Under review 
  Access Paper or Ask Questions

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones


Oct 29, 2020
Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair, Michael Luo, Krishnan Srinivasan, Minho Hwang, Joseph E. Gonzalez, Julian Ibarz, Chelsea Finn, Ken Goldberg

Figure 1 for Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Figure 2 for Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Figure 3 for Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Figure 4 for Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
* First two authors contributed equally 
  Access Paper or Ask Questions

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks


Oct 27, 2020
Jianfei Chen, Yu Gai, Zhewei Yao, Michael W. Mahoney, Joseph E. Gonzalez

Figure 1 for A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Figure 2 for A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Figure 3 for A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Figure 4 for A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
* 24 pages 
  Access Paper or Ask Questions

Multi-Agent Collaboration via Reward Attribution Decomposition


Oct 16, 2020
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian

Figure 1 for Multi-Agent Collaboration via Reward Attribution Decomposition
Figure 2 for Multi-Agent Collaboration via Reward Attribution Decomposition
Figure 3 for Multi-Agent Collaboration via Reward Attribution Decomposition
Figure 4 for Multi-Agent Collaboration via Reward Attribution Decomposition

  Access Paper or Ask Questions

MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects


Oct 09, 2020
Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Daniel Seita, Ryan Hoque, Joseph E. Gonzalez, Ken Goldberg

Figure 1 for MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects
Figure 2 for MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects
Figure 3 for MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects
* IROS 2020 Workshop on Managing Deformation: A Step Towards Higher Robot Autonomy 
  Access Paper or Ask Questions

Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting


Oct 04, 2020
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell

Figure 1 for Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Figure 2 for Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Figure 3 for Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Figure 4 for Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

  Access Paper or Ask Questions

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation


Sep 19, 2020
Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer

Figure 1 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Figure 2 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Figure 3 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Figure 4 for A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

  Access Paper or Ask Questions

Benchmarking Semi-supervised Federated Learning


Aug 26, 2020
Zhengming Zhang, Zhewei Yao, Yaoqing Yang, Yujun Yan, Joseph E. Gonzalez, Michael W. Mahoney

Figure 1 for Benchmarking Semi-supervised Federated Learning
Figure 2 for Benchmarking Semi-supervised Federated Learning
Figure 3 for Benchmarking Semi-supervised Federated Learning
Figure 4 for Benchmarking Semi-supervised Federated Learning

  Access Paper or Ask Questions

Boundary thickness and robustness in learning models


Jul 09, 2020
Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney

Figure 1 for Boundary thickness and robustness in learning models
Figure 2 for Boundary thickness and robustness in learning models
Figure 3 for Boundary thickness and robustness in learning models
Figure 4 for Boundary thickness and robustness in learning models

  Access Paper or Ask Questions

Contrastive Code Representation Learning


Jul 09, 2020
Paras Jain, Ajay Jain, Tianjun Zhang, Pieter Abbeel, Joseph E. Gonzalez, Ion Stoica

Figure 1 for Contrastive Code Representation Learning
Figure 2 for Contrastive Code Representation Learning
Figure 3 for Contrastive Code Representation Learning
Figure 4 for Contrastive Code Representation Learning

  Access Paper or Ask Questions