Sotabase

Career

· Founder, Stealth Robotics Startup (Current)2025–
· Associate Professor, Massachusetts Institute of Technology2024–
· Advisor, AI Foundry2019–2021
· Assistant Professor, Massachusetts Institute of Technology2019–2024
· Research Intern, DeepMind2016–2016
· Consultant, Cavium Inc2015–2015
· Co-Founder, SafelyYou2015–2019
· PHD Student, University of California, Berkeley2014–2018
· Research Intern, Qualcomm2013–2013
· Student Intern, Carnegie Mellon University2010–2010
· Student Intern, University of Melbourne2009–2009

Publications (147)

Curiosity-Driven Exploration by Self-Supervised Prediction
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2017
2,744
cited
Human Pose Estimation with Iterative Error Feedback
Computer Vision and Pattern Recognition · 2015
799
cited
Fully Automated Echocardiogram Interpretation in Clinical Practice
Circulation · 2018
740
cited
What makes ImageNet good for transfer learning?
arXiv.org · 2016
702
cited
Learning to Poke by Poking: Experiential Learning of Intuitive Physics
Neural Information Processing Systems · 2016
596
cited
Learning to See by Moving
IEEE International Conference on Computer Vision · 2015
566
cited
Is Conditional Generative Modeling all you need for Decision-Making?
International Conference on Learning Representations · 2022
540
cited
Analyzing the Performance of Multilayer Neural Networks for Object Recognition
European Conference on Computer Vision · 2014
458
cited
Learning to Perform Physics Experiments via Deep Reinforcement Learning
International Conference on Learning Representations · 2016
330
cited
Combining self-supervised learning and imitation for vision-based rope manipulation
IEEE International Conference on Robotics and Automation · 2017
326
cited
Zero-Shot Visual Imitation
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2018
319
cited
Rapid locomotion via reinforcement learning
Robotics: Science and Systems · 2022
317
cited
A System for General In-Hand Object Re-Orientation
Conference on Robot Learning · 2021
292
cited
Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation
IEEE International Conference on Robotics and Automation · 2021
286
cited
Learning Visual Predictive Models of Physics for Playing Billiards
International Conference on Learning Representations · 2015
273
cited
OpenEQA: Embodied Question Answering in the Era of Foundation Models
Computer Vision and Pattern Recognition · 2024
230
cited
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
International Conference on Learning Representations · 2020
185
cited
Visual dexterity: In-hand reorientation of novel and complex object shapes
Science Robotics · 2022
173
cited
3D Neural Scene Representations for Visuomotor Control
Conference on Robot Learning · 2021
155
cited
Investigating Human Priors for Playing Video Games
International Conference on Machine Learning · 2018
151
cited
Sotabase
Pulkit Agrawal | Researcher Profile | Sotabase | Sotabase