Deepak Pathak

LocoFormer: Generalist Locomotion via Long-context Adaptation CORL 2025 Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments CORL 2025 Generative Classifiers Avoid Shortcut Solutions ICLR 2025 Demonstrating LEAP Hand v2: Low-Cost, Easy-to-Assemble, High-Performance Hand for Robot Learning RSS 2025 FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning RSS 2025 DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies RSS 2025 SPIN: Simultaneous Perception Interaction and Navigation CVPR 2024 On the Surprising Effectiveness of Attention Transfer for Vision Transformers NIPS 2024 Demonstrating Learning from Humans on Open-Source Dexterous Robot Hands RSS 2024 Evaluating Text-to-Visual Generation with Image-to-Text Generation ECCV 2024 Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer ICLR 2024 Language Models as Black-Box Optimizers for Vision-Language Models CVPR 2024 SAPG: Split and Aggregate Policy Gradients ICML 2024 Revisiting the Role of Language Priors in Vision-Language Models ICML 2024 Legolas: Deep Leg-Inertial Odometry CORL 2024 Bimanual Dexterity for Complex Tasks CORL 2024 Continuously Improving Mobile Manipulation with Autonomous Real-World RL CORL 2024 LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning RSS 2023 Affordances From Human Videos as a Versatile Representation for Robotics CVPR 2023 Structured World Models from Human Videos RSS 2023 Your Diffusion Model is Secretly a Zero-Shot Classifier ICCV 2023 Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback NIPS 2023 Test-time Adaptation with Slot-Centric Models ICML 2023 FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation WACV 2023 DEFT: Dexterous Fine-Tuning for Hand Policies CORL 2023 PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play CORL 2023 Dexterous Functional Grasping CORL 2023 Internet Explorer: Targeted Representation Learning on the Open Web ICML 2023 Efficient RL via Disentangled Environment and Agent Representations ICML 2023 Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models CVPR 2023 Continual Learning with Evolving Class Ontologies NIPS 2022 Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion CORL 2022 Legged Locomotion in Challenging Terrains using Egocentric Vision CORL 2022 HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration CORL 2022 VideoDex: Learning Dexterity from Internet Videos CORL 2022 Topologically-Aware Deformation Fields for Single-View 3D Reconstruction CVPR 2022 Coupling Vision and Proprioception for Navigation of Legged Robots CVPR 2022 Understanding Collapse in Non-Contrastive Siamese Representation Learning ECCV 2022 Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents ICML 2022 REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer ICML 2022 Zero-Shot Reward Specification via Grounded Natural Language ICML 2022 Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on YouTube RSS 2022 Human-to-Robot Imitation in the Wild RSS 2022 Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives NIPS 2021 Functional Regularization for Reinforcement Learning via Learned Fourier Features NIPS 2021 Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis From a Single Image ICCV 2021 Differentiable Spatial Planning using Transformers ICML 2021 Unsupervised Learning of Visual 3D Keypoints for Control ICML 2021 Learning Long-term Visual Dynamics with Region Proposal Interaction Networks ICLR 2021 Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots CORL 2021 Discovering and Achieving Goals via World Models NIPS 2021 RMA: Rapid Motor Adaptation for Legged Robots RSS 2021 Hierarchical Neural Dynamic Policies RSS 2021 Interesting Object, Curious Agent: Learning Task-Agnostic Exploration NIPS 2021 Planning to Explore via Self-Supervised World Models ICML 2020 Neural Dynamic Policies for End-to-End Sensorimotor Learning NIPS 2020 Locally Masked Convolution for Autoregressive Models UAI 2020 Sparse Graphical Memory for Robust Planning NIPS 2020 One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control ICML 2020 Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity NIPS 2019 Large-Scale Study of Curiosity-Driven Learning ICLR 2019 Self-Supervised Exploration via Disagreement ICML 2019 Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller NIPS 2019 Investigating Human Priors for Playing Video Games ICML 2018 Zero-Shot Visual Imitation ICLR 2018 Learning Features by Watching Objects Move CVPR 2017 Curiosity-driven Exploration by Self-supervised Prediction ICML 2017 Toward Multimodal Image-to-Image Translation NIPS 2017 Large Scale Visual Recognition through Adaptation using Joint Representation and Multiple Instance Learning JMLR 2016 Context Encoders: Feature Learning by Inpainting CVPR 2016 Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning CVPR 2015 Constrained Convolutional Neural Networks for Weakly Supervised Segmentation ICCV 2015