b'Deepak Pathak'

research

∙ 05/12/2022

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

We present a framework for learning 3D object shapes and dense cross-obj...

Shivam Duggal, et al. ∙

research

∙ 03/21/2022

Generating Fast and Slow: Scene Decomposition via Reconstruction

We consider the problem of segmenting scenes into constituent entities, ...

Mihir Prabhudesai, et al. ∙

research

∙ 02/21/2022

Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube

We build a system that enables any human to control a robot hand and arm...

Aravind Sivakumar, et al. ∙

research

∙ 02/10/2022

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

A popular paradigm in robotic learning is to train a policy from scratch...

Xingyu Liu, et al. ∙

research

∙ 01/18/2022

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents

Can world knowledge learned by large language models (LLMs) be used to a...

Wenlong Huang, et al. ∙

research

∙ 01/17/2022

The CLEAR Benchmark: Continual LEArning on Real-World Imagery

Continual learning (CL) is widely regarded as crucial challenge for life...

Zhiqiu Lin, et al. ∙

research

∙ 12/06/2021

Functional Regularization for Reinforcement Learning via Learned Fourier Features

We propose a simple architecture for deep reinforcement learning by embe...

Alexander C. Li, et al. ∙

research

∙ 12/03/2021

Coupling Vision and Proprioception for Navigation of Legged Robots

We exploit the complementary strengths of vision and proprioception to a...

Zipeng Fu, et al. ∙

research

∙ 12/02/2021

Differentiable Spatial Planning using Transformers

We consider the problem of spatial path planning. In contrast to the cla...

Devendra Singh Chaplot, et al. ∙

research

∙ 11/04/2021

Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning

Dexterous manipulation of arbitrary objects, a fundamental daily task fo...

Wenlong Huang, et al. ∙

research

∙ 10/28/2021

Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives

Despite the potential of reinforcement learning (RL) for building genera...

Murtaza Dalal, et al. ∙

research

∙ 10/25/2021

Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots

Legged locomotion is commonly studied and expressed as a discrete set of...

Zipeng Fu, et al. ∙

research

∙ 10/18/2021

Discovering and Achieving Goals via World Models

How can artificial agents learn to solve many diverse tasks in complex v...

Russell Mendonca, et al. ∙

research

∙ 07/08/2021

RMA: Rapid Motor Adaptation for Legged Robots

Successful real-world deployment of legged robots would require them to ...

Ashish Kumar, et al. ∙

research

∙ 04/15/2021

Auto-Tuned Sim-to-Real Transfer

Policies trained in simulation often fail when transferred to the real w...

Yuqing Du, et al. ∙

research

∙ 12/17/2020

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

We present Worldsheet, a method for novel view synthesis using just a si...

Ronghang Hu, et al. ∙

research

∙ 12/15/2020

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

A majority of approaches solve the problem of video frame interpolation ...

Tarun Kalluri, et al. ∙

research

∙ 08/27/2020

Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion

Hierarchical learning has been successful at learning generalizable loco...

Tianyu Li, et al. ∙

research

∙ 08/05/2020

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks

Learning long-term dynamics models is the key to understanding physical ...

Haozhi Qi, et al. ∙

research

∙ 07/09/2020

One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control

Reinforcement learning is typically concerned with learning control poli...

Wenlong Huang, et al. ∙

research

∙ 06/22/2020

Locally Masked Convolution for Autoregressive Models

High-dimensional generative models have many applications including imag...

Ajay Jain, et al. ∙

research

∙ 05/12/2020

Planning to Explore via Self-Supervised World Models

Reinforcement learning allows solving complex tasks, however, the learni...

Ramanan Sekar, et al. ∙

research

∙ 03/13/2020

Sparse Graphical Memory for Robust Planning

To operate effectively in the real world, artificial agents must act fro...

Michael (Misha) Laskin, et al. ∙

research

∙ 11/21/2019

Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller

We study a generalized setup for learning from demonstration to build an...

Pratyusha Sharma, et al. ∙

research

∙ 06/10/2019

Self-Supervised Exploration via Disagreement

Efficient exploration is a long-standing problem in sensorimotor learnin...

Deepak Pathak, et al. ∙

∙ 05/17/2019

Image Inpainting

Fills holes in images

Deepak Pathak ∙

research

∙ 02/14/2019

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity

Contemporary sensorimotor learning approaches typically start with an ex...

Deepak Pathak, et al. ∙

research

∙ 08/13/2018

Large-Scale Study of Curiosity-Driven Learning

Reinforcement learning algorithms rely on carefully engineering environm...

Yuri Burda, et al. ∙

research

∙ 07/19/2018

Compositional GAN: Learning Conditional Image Composition

Generative Adversarial Networks (GANs) can produce images of surprising ...

Samaneh Azadi, et al. ∙

research

∙ 06/21/2018

Learning Instance Segmentation by Interaction

We present an approach for building an active agent that learns to segme...

Deepak Pathak, et al. ∙

research

∙ 04/23/2018

Zero-Shot Visual Imitation

The current dominant paradigm for imitation learning relies on strong su...

Deepak Pathak, et al. ∙

research

∙ 02/28/2018

Investigating Human Priors for Playing Video Games

What makes humans so good at solving seemingly complex video games? Unli...

Rachit Dubey, et al. ∙

research

∙ 11/30/2017

Toward Multimodal Image-to-Image Translation

Many image-to-image translation problems are ambiguous, as a single inpu...

Jun-Yan Zhu, et al. ∙

research

∙ 05/15/2017

Curiosity-driven Exploration by Self-supervised Prediction

In many real-world scenarios, rewards extrinsic to the agent are extreme...

Deepak Pathak, et al. ∙

research

∙ 12/19/2016

Learning Features by Watching Objects Move

This paper presents a novel yet intuitive approach to unsupervised featu...

Deepak Pathak, et al. ∙

research

∙ 04/25/2016

Context Encoders: Feature Learning by Inpainting

We present an unsupervised visual feature learning algorithm driven by c...

Deepak Pathak, et al. ∙

research

∙ 06/11/2015

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

We present an approach to learn a dense pixel-wise labeling from image-l...

Deepak Pathak, et al. ∙

research

∙ 12/22/2014

Fully Convolutional Multi-Class Multiple Instance Learning

Multiple instance learning (MIL) can reduce the need for costly annotati...

Deepak Pathak, et al. ∙

research

∙ 12/02/2014

Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning

We develop methods for detector learning which exploit joint training ov...

Judy Hoffman, et al. ∙

Deepak Pathak

Featured Co-authors