Deepak Pathak

Affiliations

Carnegie Mellon University

papers

2,079

total citations

papers (23)

Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models

CVPR 2023arXiv

157

citations

Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives

NEURIPS 2021arXiv

113

citations

Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis From a Single Image

ICCV 2021arXiv

citations

Coupling Vision and Proprioception for Navigation of Legged Robots

CVPR 2022arXiv

citations

Neural Dynamic Policies for End-to-End Sensorimotor Learning

NEURIPS 2020arXiv

citations

Sparse Graphical Memory for Robust Planning

NEURIPS 2020arXiv

citations

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration

NEURIPS 2021arXiv

citations

Topologically-Aware Deformation Fields for Single-View 3D Reconstruction

CVPR 2022arXiv

citations

Understanding Collapse in Non-Contrastive Siamese Representation Learning

ECCV 2022arXiv

citations

Language Models as Black-Box Optimizers for Vision-Language Models

CVPR 2024arXiv

citations

Revisiting the Role of Language Priors in Vision-Language Models

ICML 2024arXiv

citations

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

NEURIPS 2023arXiv

citations

SPIN: Simultaneous Perception Interaction and Navigation

CVPR 2024arXiv

citations

Diffusion Beats Autoregressive in Data-Constrained Settings

NEURIPS 2025arXiv

citations

Functional Regularization for Reinforcement Learning via Learned Fourier Features

NEURIPS 2021arXiv

citations

SAPG: Split and Aggregate Policy Gradients

ICML 2024arXiv

citations

Generative Classifiers Avoid Shortcut Solutions

ICLR 2025arXiv

citations

Continual Learning with Evolving Class Ontologies

NEURIPS 2022arXiv

citations

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer

ICLR 2024arXiv

citations

Deepak Pathak

Affiliations

papers (23)

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Your Diffusion Model is Secretly a Zero-Shot Classifier

Affordances From Human Videos as a Versatile Representation for Robotics

Discovering and Achieving Goals via World Models

Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models

Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives

Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis From a Single Image

Coupling Vision and Proprioception for Navigation of Legged Robots

Neural Dynamic Policies for End-to-End Sensorimotor Learning

Sparse Graphical Memory for Robust Planning

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration

Topologically-Aware Deformation Fields for Single-View 3D Reconstruction

Understanding Collapse in Non-Contrastive Siamese Representation Learning

Language Models as Black-Box Optimizers for Vision-Language Models

Revisiting the Role of Language Priors in Vision-Language Models

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

SPIN: Simultaneous Perception Interaction and Navigation

Diffusion Beats Autoregressive in Data-Constrained Settings

Functional Regularization for Reinforcement Learning via Learned Fourier Features

SAPG: Split and Aggregate Policy Gradients

Generative Classifiers Avoid Shortcut Solutions

Continual Learning with Evolving Class Ontologies

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer

papers (23)

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Your Diffusion Model is Secretly a Zero-Shot Classifier

Affordances From Human Videos as a Versatile Representation for Robotics

Discovering and Achieving Goals via World Models

Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models

Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives

Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis From a Single Image

Coupling Vision and Proprioception for Navigation of Legged Robots

Neural Dynamic Policies for End-to-End Sensorimotor Learning

Sparse Graphical Memory for Robust Planning

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration

Topologically-Aware Deformation Fields for Single-View 3D Reconstruction

Understanding Collapse in Non-Contrastive Siamese Representation Learning

Language Models as Black-Box Optimizers for Vision-Language Models

Revisiting the Role of Language Priors in Vision-Language Models

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

SPIN: Simultaneous Perception Interaction and Navigation

Diffusion Beats Autoregressive in Data-Constrained Settings

Functional Regularization for Reinforcement Learning via Learned Fourier Features

SAPG: Split and Aggregate Policy Gradients

Generative Classifiers Avoid Shortcut Solutions

Continual Learning with Evolving Class Ontologies

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer