Sotabase

Career

· Angel Investor, Deepak Pathak (Current)2023–
· Co-Founder CEO, Skild AI2023–
· Assistant Professor, Carnegie Mellon University2020–
· Researcher, Facebook AI2019–2020
· Doctor of Philosophy - PhD, Artificial Intelligence, University of California, Berkeley2014–2019
· PHD Student, University of California, Berkeley2014–2019
· Co-Founder, VisageMap Inc.2014–2016
· Research Intern, Microsoft2013–2013
· Bachelor of Technology - BTech, Computer Science, Indian Institute of Technology, Kanpur2010–2014

Publications (132)

Context Encoders: Feature Learning by Inpainting
Computer Vision and Pattern Recognition · 2016
5,635
cited
Curiosity-Driven Exploration by Self-Supervised Prediction
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2017
2,744
cited
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
International Conference on Machine Learning · 2022
1,434
cited
Toward Multimodal Image-to-Image Translation
Neural Information Processing Systems · 2017
1,425
cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0
IEEE International Conference on Robotics and Automation · 2023
785
cited
RMA: Rapid Motor Adaptation for Legged Robots
Robotics: Science and Systems · 2021
757
cited
Large-Scale Study of Curiosity-Driven Learning
International Conference on Learning Representations · 2018
747
cited
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
IEEE International Conference on Computer Vision · 2015
639
cited
Learning Features by Watching Objects Move
Computer Vision and Pattern Recognition · 2016
534
cited
Planning to Explore via Self-Supervised World Models
International Conference on Machine Learning · 2020
473
cited
Self-Supervised Exploration via Disagreement
International Conference on Machine Learning · 2019
429
cited
Fully Convolutional Multi-Class Multiple Instance Learning
International Conference on Learning Representations · 2014
323
cited
Zero-Shot Visual Imitation
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2018
319
cited
Your Diffusion Model is Secretly a Zero-Shot Classifier
IEEE International Conference on Computer Vision · 2023
318
cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration
IEEE International Conference on Robotics and Automation · 2024
282
cited
Legged Locomotion in Challenging Terrains using Egocentric Vision
Conference on Robot Learning · 2022
276
cited
Affordances from Human Videos as a Versatile Representation for Robotics
Computer Vision and Pattern Recognition · 2023
261
cited
Human-to-Robot Imitation in the Wild
Robotics: Science and Systems · 2022
224
cited
Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion
Conference on Robot Learning · 2022
223
cited
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
International Conference on Machine Learning · 2020
203
cited
Sotabase