Publications
2024
Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features
International Conference on Learning Representations (ICLR), 2024
(Spotlight)
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
International Conference on Learning Representations (ICLR), 2024
AutoFT: Robust Fine-Tuning by Optimizing Hyperparameters on OOD Data
2023
Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning
Conference on Robot Learning (CoRL), 2023
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Conference on Robot Learning (CoRL), 2023
Bridgedata v2: A dataset for robot learning at scale
Conference on Robot Learning (CoRL), 2023
Waypoint-based imitation learning for robotic manipulation
Conference on Robot Learning (CoRL), 2023
Polybot: Training One Policy Across Robots While Embracing Variability
Conference on Robot Learning (CoRL), 2023
Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning
Conference on Robot Learning (CoRL), 2023
Open-world object manipulation using pre-trained vision-language models
Conference on Robot Learning (CoRL), 2023
Roboclip: one demonstration is enough to learn robot policies
Neural Information Processing Systems (NeurIPS), 2023
Direct preference optimization: Your language model is secretly a reward model
Neural Information Processing Systems (NeurIPS), 2023
Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning
Neural Information Processing Systems (NeurIPS), 2023
Permutation Equivariant Neural Functionals
Neural Information Processing Systems (NeurIPS), 2023
Disentanglement via Latent Quantization
Neural Information Processing Systems (NeurIPS), 2023
Self-destructing models: Increasing the costs of harmful dual uses of foundation models
AAAI/ACM Conference on AI, Ethics, and Society, 2023
Learning fine-grained bimanual manipulation with low-cost hardware
Robotics: Science and Systems (RSS), 2023
Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets
Robotics: Science and Systems (RSS), 2023
Language-driven representation learning for robotics
Robotics: Science and Systems (RSS), 2023
Pre-training for robots: Offline rl enables learning new tasks from a handful of trials
Robotics: Science and Systems (RSS), 2023
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
International Conference on Machine Learning (ICML), 2023
(Oral)
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
A Control-Centric Benchmark for Video Prediction
International Conference on Learning Representations (ICLR), 2023
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
International Conference on Learning Representations (ICLR), 2023
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
International Conference on Learning Representations (ICLR), 2023
Diversify and disambiguate: Out-of-distribution robustness via disagreement
International Conference on Learning Representations (ICLR), 2023
Model-Based Adversarial Imitation Learning As Online Fine-Tuning
Workshop on Reincarnating Reinforcement Learning at International Conference on Learning Representations (ICLR), 2023
Train Offline, Test Online: A Real Robot Learning Benchmark
International Conference on Robotics and Automation (ICRA), 2023
Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment
Interactive Model Correction with Natural Language
Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning
Contrastive Preference Learning: Learning from Human Feedback without RL
An Emulator for Fine-Tuning Large Language Models using Small Language Models
Zero-shot robotic manipulation with pretrained image-editing diffusion models
Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias
Analyzing and mitigating object hallucination in large vision-language models
Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations
Decomposing the generalization gap in imitation learning for visual robotic manipulation
Leveraging domain relations for domain generalization
Conservative Prediction via Transductive Confidence Minimization
Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts
2022
Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning
Neural Information Processing Systems (NeurIPS), 2022
You Only Live Once: Single Life Reinforcement Learning
Neural Information Processing Systems (NeurIPS), 2022
C-Mixup: Improving Generalization in Regression
Neural Information Processing Systems (NeurIPS), 2022
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Neural Information Processing Systems (NeurIPS), 2022
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
Neural Information Processing Systems (NeurIPS) Datasets & Benchmarks Track, 2022
Relaxing the Kolmogorov Structure Function for Realistic Computational Constraints
InfoCog Workshop at Neural Information Processing Systems (NeurIPS), 2022
Training and Evaluation of Deep Policies Using Reinforcement Learning and Generative Models
Journal of Machine Learning Research (JMLR), 2022
R3M: A Universal Visual Representation for Robot Manipulation
Conference on Robot Learning (CoRL), 2022
Offline Reinforcement Learning at Multiple Frequencies
Conference on Robot Learning (CoRL), 2022
Lifelong Robotic Reinforcement Learning by Retaining Experiences
Conference on Lifelong Learning Agents (CoLLAs), 2022
Memory-Based Model Editing at Scale
International Conference on Machine Learning (ICML), 2022
Improving Out-of-Distribution Robustness via Selective Augmentation
International Conference on Machine Learning (ICML), 2022
How to Leverage Unlabeled Data in Offline Reinforcement Learning
International Conference on Machine Learning (ICML), 2022
Robust Policy Learning over Multiple Uncertainty Sets
International Conference on Machine Learning (ICML), 2022
A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
International Conference on Machine Learning (ICML), 2022
Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations
International Conference on Machine Learning (ICML), 2022
Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning
Robotics: Science and Systems (RSS), 2022
Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
Robotics: Science and Systems (RSS), 2022
Vision-Based Manipulators Need to Also See from Their Hands
International Conference on Learning Representations (ICLR), 2022
(Oral)
Autonomous Reinforcement Learning: Formalism and Benchmarking
International Conference on Learning Representations (ICLR), 2022
Do Deep Networks Transfer Invariances Across Classes?
International Conference on Learning Representations (ICLR), 2022
Extending the WILDS Benchmark for Unsupervised Adaptation
International Conference on Learning Representations (ICLR), 2022
(Oral)
2021
Information is Power: Intrinsic Control via Information Capture
Neural Information Processing Systems (NeurIPS), 2021
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
Neural Information Processing Systems (NeurIPS), 2021
COMBO: Conservative Offline Model-Based Policy Optimization
Neural Information Processing Systems (NeurIPS), 2021
Visual Adversarial Imitation Learning using Variational Models
Neural Information Processing Systems (NeurIPS), 2021
Autonomous Reinforcement Learning via Subgoal Curricula
Neural Information Processing Systems (NeurIPS), 2021
Example-Based Offline Reinforcement Learning without Rewards
NeurIPS Offline Reinforcement Learning Workshop, 2021
Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks
Conference on Robot Learning (CoRL), 2021
A Workflow for Offline Model-Free Robotic Reinforcement Learning
Conference on Robot Learning (CoRL), 2021
Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation
Conference on Robot Learning (CoRL), 2021
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
Conference on Robot Learning (CoRL), 2021
Learning Generalizable Robotic Reward Functions from In-The-Wild Human Videos
Robotics: Science and Systems (RSS), 2021
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
International Conference on Machine Learning (ICML), 2021
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
International Conference on Machine Learning (ICML), 2021
Just Train Twice: Improving Group Robustness without Training Group Information
International Conference on Machine Learning (ICML), 2021
(Long Talk)
WILDS: A Benchmark of in the Wild Distribution Shifts
International Conference on Machine Learning (ICML), 2021
(Long Talk)
Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Offline Reinforcement Learning from Images with Latent Space Models
Learning for Decision Making and Control (L4DC), 2021
Batch Exploration with Examples for Scalable Robotic Reinforcement Learning
Robotics and Automation Letters (RA-L). International Conference on Robotics and Automation (ICRA), 2021
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Robotics and Automation Letters (RA-L). International Conference on Robotics and Automation (ICRA)
How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
International Journal of Robotics Research (IJRR), 2021
Model-Based Visual Planning with Self-Supervised Functional Distances
International Conference on Learning Representations (ICLR), 2021
(Spotlight)
SMiRL: Surprise Minimizing RL in Dynamic Environments
International Conference on Learning Representations (ICLR), 2021
(Oral)
2020
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Conference on Robot Learning (CoRL), 2020
(Oral)
Learning Latent Representations to Influence Multi-Agent Interaction
Conference on Robot Learning (CoRL), 2020
(Oral, Best Paper Award)
Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
Conference on Robot Learning (CoRL), 2020
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
Neural Information Processing Systems (NeurIPS), 2020
Continual Learning of Control Primitives: Skill Discovery via Reset-Games
Neural Information Processing Systems (NeurIPS)
Gradient Surgery for Multi-Task Learning
Neural Information Processing Systems (NeurIPS), 2020
Weakly-Supervised Reinforcement Learning for Controllable Behavior
Neural Information Processing Systems (NeurIPS), 2020
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Neural Information Processing Systems (NeurIPS), 2020
Learning Predictive Models From Observation and Interaction
European Conference on Computer Vision (ECCV), 2020
Goal-Aware Prediction: Learning to Model What Matters
International Conference on Machine Learning (ICML), 2020
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
International Conference on Machine Learning (ICML), 2020
Scalable Multi-Task Imitation Learning with Autonomous Improvement
International Conference on Robotics and Automation (ICRA), 2020
Time Reversal as Self-Supervision
International Conference on Robotics and Automation (ICRA), 2020
OmniTact: Compact Multi-Directional Optical Tactile Sensor for Robotic Manipulation
International Conference on Robotics and Automation (ICRA), 2020
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
International Conference on Learning Representations (ICLR), 2020
Model-Based Reinforcement Learning for Atari
International Conference on Learning Representations (ICLR), 2020
(Spotlight)
VideoFlow: A Flow-Based Generative Model for Video
International Conference on Learning Representations (ICLR), 2020
Learning to Interactively Learn and Assist
AAAI Conference on Artificial Intelligence, 2020
(Oral)
2019
RoboNet: Large-Scale Multi-Robot Learning
Conference on Robot Learning (CoRL), 2019
Language as an Abstraction for Hierarchical Reinforcement Learning
Neural Information Processing Systems (NeurIPS), 2019
Guided Meta-Policy Search
Neural Information Processing Systems (NeurIPS)
(Spotlight)
One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
International Conference on Intelligent Robots and Systems (IROS), 2019
End-to-End Robotic Reinforcement Learning without Reward Engineering
Robotics: Science and Systems (RSS), 2019
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
Robotics: Science and Systems (RSS), 2019
Unsupervised Visuomotor Control Through Distributional Planning Networks
Robotics: Science and Systems (RSS), 2019
Manipulation by Feel: Touch-Based Control with Deep Predictive Models
International Conference on Robotics and Automation (ICRA), 2019
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
International Conference on Learning Representations (ICLR), 2019
2018
Robustness via Retrying: Closed-Loop Robotic Manipulation via Self-Supervised Learning
Conference on Learning (CoRL), 2018
Stochastic Variational Video Prediction
International Conference on Learning Representations (ICLR), 2018
Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
International Conference on Robotics and Automation (ICRA), 2018
2017
Self-Supervised Visual Planning with Temporal Skip Connections
Conference on Robot Learning (CoRL), 2017
(Long Talk)
Generalizing Skills with Semi-Supervised Reinforcement Learning
International Conference on Learning Representations (ICLR), 2017
Deep Visual Foresight for Planning Robot Motion
International Conference on Robotics and Automation (ICRA), 2017
(Best Cognitive Robotics Paper Finalist)
Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States
International Conference on Robotics and Automation (ICRA), 2017
2016
A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
NIPS Workshop on Adversarial Training, 2016
Unsupervised Learning for Physical Interaction through Video Prediction
Neural Information Processing Systems (NIPS), 2016
Adapting Deep Visuomotor Representations with Weak Pairwise Constraints
Workshop on the Algorithmic Foundations of Robotics (WAFR), 2016
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
International Conference on Machine Learning (ICML), 2016
End-to-End Training of Deep Visuomotor Policies
Journal of Machine Learning Research (JMLR), 2016
Learning Deep Neural Network Policies with Continuous Memory States
International Conference on Robotics and Automation (ICRA), 2016
Deep Spatial Autoencoders for Visuomotor Learning
International Conference on Robotics and Automation (ICRA), 2016