Research

DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
Robotics: Science and Systems (RSS), 2025   [Oral Presentation]
Tony Tao*, Mohan Kumar Srirama*, Jason Liu, Kenny Shaw, Deepak Pathak
PDF Cite Code Project Video
DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
Policy Agnostic RL Fine-Tuning Multiple Policy Classes with Actor-Critic RL
ICLR Generative Models for Robot Learning Worshop, 2025   [Best Paper Award]
Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio, Mohan Kumar Srirama, Archit Sharma, Chelsea Finn, Aviral Kumar
PDF Cite Code Project Video
Policy Agnostic RL Fine-Tuning Multiple Policy Classes with Actor-Critic RL
HRP: Human Affordances for Robotic Pre-Training
Robotics: Science and Systems (RSS), 2024   [Oral Presentation]
Mohan Kumar Srirama, Sudeep Dasari, Shikhar Bahl, Abhinav Gupta
PDF Cite Code Project Video
HRP: Human Affordances for Robotic Pre-Training
The Ingredients for Robotic Diffusion Transformers
IEEE International Conference on Robotics and Automation (ICRA), 2025
Sudeep Dasari, Oier Mees, Sebastian Zhao, Mohan Kumar Srirama, Sergey Levine
PDF Cite Code Project Video
The Ingredients for Robotic Diffusion Transformers
Bimanual Dexterity for Complex Tasks
Conference on Robot Learning (CoRL) 2024
Kenneth Shaw*, Yulong Li*, Jiahui Yang, Mohan Kumar Srirama, Ray Liu, Haoyu Xiong, Russell Mendonca, Deepak Pathak
PDF Cite Code Project Video
Bimanual Dexterity for Complex Tasks
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Robotics: Science and Systems (RSS), 2024  [Oral Presentation]
Alexander Khazatsky*, Karl Pertsch*, Suraj Nair, Ashwin Balakrishna, Sudeep Dasari, Siddharth Karamcheti, Soroush Nasiriany, Mohan Kumar Srirama, ------, Sergey Levine, Chelsea Finn
PDF Cite Code Project Video
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
IEEE International Conference on Robotics and Automation (ICRA), 2024   [Best Paper Award]
Open X-Embodiment Collaboration
PDF Cite Code Project Video
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
An Unbiased Look at Datasets for Visuo-Motor Pre-Training
Conference on Robot Learning (CoRL), 2023
Sudeep Dasari, Mohan Kumar Srirama, Unnat Jain, Abhinav Gupta
PDF Cite Code Project Video
An Unbiased Look at Datasets for Visuo-Motor Pre-Training
Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations
International Conference on Computer Vision (ICCV), 2023   [Oral Presentation]
Jianren Wang*, Sudeep Dasari, Mohan Kumar Srirama, Shubham Tulsiani, Abhinav Gupta
PDF Cite Code Project Video
Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations
Train Offline, Test Online: A Real Robot Learning Benchmark (TOTO)
IEEE International Conference on Robotics and Automation (ICRA), 2023 [Best Paper Award at NeurIPS WBRC 2022]
Gaoyue Zhou*, Victoria Dean*, Mohan Kumar Srirama, Aravind Rajeswaran, Jyothish Pari, Kyle Hatch, Aryan Jain, Tianhe Yu, Pieter Abbeel, Lerrel Pinto, Chelsea Finn, Abhinav Gupta
PDF Cite Code Project Video
Train Offline, Test Online: A Real Robot Learning Benchmark (TOTO)