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 Yuke Zhu

Yuke Zhu

Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization


Nov 15, 2021
Youngwoon Lee, Joseph J. Lim, Anima Anandkumar, Yuke Zhu

Figure 1 for Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization
Figure 2 for Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization
Figure 3 for Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization
Figure 4 for Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization
* Published at the Conference on Robot Learning (CoRL) 2021 
  Access Paper or Ask Questions

Reinforcement Learning in Factored Action Spaces using Tensor Decompositions


Oct 27, 2021
Anuj Mahajan, Mikayel Samvelyan, Lei Mao, Viktor Makoviychuk, Animesh Garg, Jean Kossaifi, Shimon Whiteson, Yuke Zhu, Animashree Anandkumar

Figure 1 for Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
Figure 2 for Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
Figure 3 for Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
Figure 4 for Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
* 2nd Workshop on Quantum Tensor Networks in Machine Learning (NeurIPS 2021) 
  Access Paper or Ask Questions

Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks


Oct 07, 2021
Soroush Nasiriany, Huihan Liu, Yuke Zhu

Figure 1 for Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
Figure 2 for Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
Figure 3 for Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
Figure 4 for Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks

  Access Paper or Ask Questions

OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation


Oct 02, 2021
Josiah Wong, Viktor Makoviychuk, Anima Anandkumar, Yuke Zhu

Figure 1 for OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation
Figure 2 for OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation
Figure 3 for OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation
Figure 4 for OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation

  Access Paper or Ask Questions

Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation


Sep 28, 2021
Yifeng Zhu, Peter Stone, Yuke Zhu

Figure 1 for Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
Figure 2 for Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
Figure 3 for Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
Figure 4 for Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
* Submitted to RA-L (ICRA 2022) 
  Access Paper or Ask Questions

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation


Aug 06, 2021
Ajay Mandlekar, Danfei Xu, Josiah Wong, Soroush Nasiriany, Chen Wang, Rohun Kulkarni, Li Fei-Fei, Silvio Savarese, Yuke Zhu, Roberto Martín-Martín

Figure 1 for What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Figure 2 for What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Figure 3 for What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Figure 4 for What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

  Access Paper or Ask Questions

MultiBench: Multiscale Benchmarks for Multimodal Representation Learning


Jul 15, 2021
Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Chen, Peter Wu, Michelle A. Lee, Yuke Zhu, Ruslan Salakhutdinov, Louis-Philippe Morency

Figure 1 for MultiBench: Multiscale Benchmarks for Multimodal Representation Learning
Figure 2 for MultiBench: Multiscale Benchmarks for Multimodal Representation Learning
* Code: https://github.com/pliang279/MultiBench and Website: https://cmu-multicomp-lab.github.io/multibench/ 
  Access Paper or Ask Questions

Discovering Generalizable Skills via Automated Generation of Diverse Tasks


Jun 26, 2021
Kuan Fang, Yuke Zhu, Silvio Savarese, Li Fei-Fei

Figure 1 for Discovering Generalizable Skills via Automated Generation of Diverse Tasks
Figure 2 for Discovering Generalizable Skills via Automated Generation of Diverse Tasks
Figure 3 for Discovering Generalizable Skills via Automated Generation of Diverse Tasks
Figure 4 for Discovering Generalizable Skills via Automated Generation of Diverse Tasks
* RSS 2021 
  Access Paper or Ask Questions

SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies


Jun 17, 2021
Linxi Fan, Guanzhi Wang, De-An Huang, Zhiding Yu, Li Fei-Fei, Yuke Zhu, Anima Anandkumar

Figure 1 for SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Figure 2 for SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Figure 3 for SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Figure 4 for SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
* ICML 2021. Website: https://linxifan.github.io/secant-site/ 
  Access Paper or Ask Questions

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision


Jun 05, 2021
Shiyi Lan, Zhiding Yu, Christopher Choy, Subhashree Radhakrishnan, Guilin Liu, Yuke Zhu, Larry S. Davis, Anima Anandkumar

Figure 1 for DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Figure 2 for DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Figure 3 for DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Figure 4 for DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
* Tech Report 
  Access Paper or Ask Questions

Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning


May 31, 2021
Anuj Mahajan, Mikayel Samvelyan, Lei Mao, Viktor Makoviychuk, Animesh Garg, Jean Kossaifi, Shimon Whiteson, Yuke Zhu, Animashree Anandkumar

Figure 1 for Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Figure 2 for Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Figure 3 for Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Figure 4 for Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
* 38th International Conference on Machine Learning, PMLR 139, 2021 
  Access Paper or Ask Questions

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition


May 18, 2021
Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Animashree Anandkumar

Figure 1 for Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
Figure 2 for Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
Figure 3 for Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
Figure 4 for Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

  Access Paper or Ask Questions

Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations


Apr 04, 2021
Zhenyu Jiang, Yifeng Zhu, Maxwell Svetlik, Kuan Fang, Yuke Zhu

Figure 1 for Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
Figure 2 for Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
Figure 3 for Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
Figure 4 for Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations

  Access Paper or Ask Questions

Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales


Mar 22, 2021
Yifan Sun, Yuke Zhu, Yuhan Zhang, Pengkun Zheng, Xi Qiu, Chi Zhang, Yichen Wei

Figure 1 for Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
Figure 2 for Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
Figure 3 for Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
Figure 4 for Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
* 8pages, accepted by CVPR 2021 
  Access Paper or Ask Questions

Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects


Dec 22, 2020
Xinlei Pan, Animesh Garg, Animashree Anandkumar, Yuke Zhu

Figure 1 for Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Figure 2 for Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Figure 3 for Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Figure 4 for Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
* 8 pages, 5 figures, Project website: https://xinleipan.github.io/emergent_morphology/ 
  Access Paper or Ask Questions

Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs


Dec 14, 2020
Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Yuke Zhu

Figure 1 for Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
Figure 2 for Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
Figure 3 for Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
Figure 4 for Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs

  Access Paper or Ask Questions

Learning Multi-Arm Manipulation Through Collaborative Teleoperation


Dec 12, 2020
Albert Tung, Josiah Wong, Ajay Mandlekar, Roberto Martín-Martín, Yuke Zhu, Li Fei-Fei, Silvio Savarese

Figure 1 for Learning Multi-Arm Manipulation Through Collaborative Teleoperation
Figure 2 for Learning Multi-Arm Manipulation Through Collaborative Teleoperation
Figure 3 for Learning Multi-Arm Manipulation Through Collaborative Teleoperation
Figure 4 for Learning Multi-Arm Manipulation Through Collaborative Teleoperation
* First two authors contributed equally 
  Access Paper or Ask Questions

Human-in-the-Loop Imitation Learning using Remote Teleoperation


Dec 12, 2020
Ajay Mandlekar, Danfei Xu, Roberto Martín-Martín, Yuke Zhu, Li Fei-Fei, Silvio Savarese

Figure 1 for Human-in-the-Loop Imitation Learning using Remote Teleoperation
Figure 2 for Human-in-the-Loop Imitation Learning using Remote Teleoperation
Figure 3 for Human-in-the-Loop Imitation Learning using Remote Teleoperation
Figure 4 for Human-in-the-Loop Imitation Learning using Remote Teleoperation

  Access Paper or Ask Questions

Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors


Dec 01, 2020
Michelle A. Lee, Matthew Tan, Yuke Zhu, Jeannette Bohg

Figure 1 for Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors
Figure 2 for Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors
Figure 3 for Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors
Figure 4 for Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors
* 8 pages, 5 figures 
  Access Paper or Ask Questions

Deep Affordance Foresight: Planning Through What Can Be Done in the Future


Nov 17, 2020
Danfei Xu, Ajay Mandlekar, Roberto Martín-Martín, Yuke Zhu, Silvio Savarese, Li Fei-Fei

Figure 1 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Figure 2 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Figure 3 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Figure 4 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future

  Access Paper or Ask Questions

Fast Uncertainty Quantification for Deep Object Pose Estimation


Nov 16, 2020
Guanya Shi, Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Fabio Ramos, Animashree Anandkumar, Yuke Zhu

Figure 1 for Fast Uncertainty Quantification for Deep Object Pose Estimation
Figure 2 for Fast Uncertainty Quantification for Deep Object Pose Estimation
Figure 3 for Fast Uncertainty Quantification for Deep Object Pose Estimation
Figure 4 for Fast Uncertainty Quantification for Deep Object Pose Estimation
* Video and code are available at https://sites.google.com/view/fastuq 
  Access Paper or Ask Questions

Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion


Oct 05, 2020
Xingye Da, Zhaoming Xie, David Hoeller, Byron Boots, Animashree Anandkumar, Yuke Zhu, Buck Babich, Animesh Garg

Figure 1 for Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
Figure 2 for Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
Figure 3 for Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
Figure 4 for Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
* supplementary video: https://youtu.be/JJOmFZKpYTo 
  Access Paper or Ask Questions

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning


Oct 02, 2020
Weili Nie, Zhiding Yu, Lei Mao, Ankit B. Patel, Yuke Zhu, Animashree Anandkumar

Figure 1 for Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Figure 2 for Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Figure 3 for Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Figure 4 for Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
* 21 pages, NeurIPS 2020 
  Access Paper or Ask Questions

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning


Sep 25, 2020
Yuke Zhu, Josiah Wong, Ajay Mandlekar, Roberto Martín-Martín

Figure 1 for robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
Figure 2 for robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
Figure 3 for robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
Figure 4 for robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
* For more information, please visit https://robosuite.ai 
  Access Paper or Ask Questions

OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation


Aug 17, 2020
Hongyu Ren, Yuke Zhu, Jure Leskovec, Anima Anandkumar, Animesh Garg

Figure 1 for OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
Figure 2 for OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
Figure 3 for OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
Figure 4 for OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
* UAI 2020 
  Access Paper or Ask Questions

Spherical Feature Transform for Deep Metric Learning


Aug 04, 2020
Yuke Zhu, Yan Bai, Yichen Wei

Figure 1 for Spherical Feature Transform for Deep Metric Learning
Figure 2 for Spherical Feature Transform for Deep Metric Learning
Figure 3 for Spherical Feature Transform for Deep Metric Learning
Figure 4 for Spherical Feature Transform for Deep Metric Learning
* ECCV2020 
  Access Paper or Ask Questions

Adaptive Procedural Task Generation for Hard-Exploration Problems


Jul 01, 2020
Kuan Fang, Yuke Zhu, Silvio Savarese, Li Fei-Fei

Figure 1 for Adaptive Procedural Task Generation for Hard-Exploration Problems
Figure 2 for Adaptive Procedural Task Generation for Hard-Exploration Problems
Figure 3 for Adaptive Procedural Task Generation for Hard-Exploration Problems
Figure 4 for Adaptive Procedural Task Generation for Hard-Exploration Problems
* 16 pages, 11 figures 
  Access Paper or Ask Questions