Alert button
Picture for Michael Ryoo

Michael Ryoo

Alert button

SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention

Dec 04, 2023
Isabel Leal, Krzysztof Choromanski, Deepali Jain, Avinava Dubey, Jake Varley, Michael Ryoo, Yao Lu, Frederick Liu, Vikas Sindhwani, Quan Vuong, Tamas Sarlos, Ken Oslund, Karol Hausman, Kanishka Rao

Figure 1 for SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention
Figure 2 for SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention
Figure 3 for SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention
Figure 4 for SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention
Viaarxiv icon

Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders

Oct 31, 2023
Srijan Das, Tanmay Jain, Dominick Reilly, Pranav Balaji, Soumyajit Karmakar, Shyam Marjit, Xiang Li, Abhijit Das, Michael Ryoo

Viaarxiv icon

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Jul 28, 2023
Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, Pete Florence, Chuyuan Fu, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Kehang Han, Karol Hausman, Alexander Herzog, Jasmine Hsu, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Isabel Leal, Lisa Lee, Tsang-Wei Edward Lee, Sergey Levine, Yao Lu, Henryk Michalewski, Igor Mordatch, Karl Pertsch, Kanishka Rao, Krista Reymann, Michael Ryoo, Grecia Salazar, Pannag Sanketi, Pierre Sermanet, Jaspiar Singh, Anikait Singh, Radu Soricut, Huong Tran, Vincent Vanhoucke, Quan Vuong, Ayzaan Wahid, Stefan Welker, Paul Wohlhart, Jialin Wu, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Tianhe Yu, Brianna Zitkovich

Figure 1 for RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Figure 2 for RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Figure 3 for RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Figure 4 for RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Viaarxiv icon

Language-based Action Concept Spaces Improve Video Self-Supervised Learning

Jul 20, 2023
Kanchana Ranasinghe, Michael Ryoo

Figure 1 for Language-based Action Concept Spaces Improve Video Self-Supervised Learning
Figure 2 for Language-based Action Concept Spaces Improve Video Self-Supervised Learning
Figure 3 for Language-based Action Concept Spaces Improve Video Self-Supervised Learning
Figure 4 for Language-based Action Concept Spaces Improve Video Self-Supervised Learning
Viaarxiv icon

RT-1: Robotics Transformer for Real-World Control at Scale

Dec 13, 2022
Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Tomas Jackson, Sally Jesmonth, Nikhil J Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Isabel Leal, Kuang-Huei Lee, Sergey Levine, Yao Lu, Utsav Malla, Deeksha Manjunath, Igor Mordatch, Ofir Nachum, Carolina Parada, Jodilyn Peralta, Emily Perez, Karl Pertsch, Jornell Quiambao, Kanishka Rao, Michael Ryoo, Grecia Salazar, Pannag Sanketi, Kevin Sayed, Jaspiar Singh, Sumedh Sontakke, Austin Stone, Clayton Tan, Huong Tran, Vincent Vanhoucke, Steve Vega, Quan Vuong, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Tianhe Yu, Brianna Zitkovich

Figure 1 for RT-1: Robotics Transformer for Real-World Control at Scale
Figure 2 for RT-1: Robotics Transformer for Real-World Control at Scale
Figure 3 for RT-1: Robotics Transformer for Real-World Control at Scale
Figure 4 for RT-1: Robotics Transformer for Real-World Control at Scale
Viaarxiv icon

Neural Neural Textures Make Sim2Real Consistent

Jun 27, 2022
Ryan Burgert, Jinghuan Shang, Xiang Li, Michael Ryoo

Figure 1 for Neural Neural Textures Make Sim2Real Consistent
Figure 2 for Neural Neural Textures Make Sim2Real Consistent
Figure 3 for Neural Neural Textures Make Sim2Real Consistent
Figure 4 for Neural Neural Textures Make Sim2Real Consistent
Viaarxiv icon

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Apr 01, 2022
Andy Zeng, Adrian Wong, Stefan Welker, Krzysztof Choromanski, Federico Tombari, Aveek Purohit, Michael Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, Pete Florence

Figure 1 for Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Figure 2 for Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Figure 3 for Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Figure 4 for Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Viaarxiv icon

Self-supervised Video Transformer

Dec 02, 2021
Kanchana Ranasinghe, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan, Michael Ryoo

Figure 1 for Self-supervised Video Transformer
Figure 2 for Self-supervised Video Transformer
Figure 3 for Self-supervised Video Transformer
Figure 4 for Self-supervised Video Transformer
Viaarxiv icon

Adaptive Intermediate Representations for Video Understanding

Apr 14, 2021
Juhana Kangaspunta, AJ Piergiovanni, Rico Jonschkowski, Michael Ryoo, Anelia Angelova

Figure 1 for Adaptive Intermediate Representations for Video Understanding
Figure 2 for Adaptive Intermediate Representations for Video Understanding
Figure 3 for Adaptive Intermediate Representations for Video Understanding
Figure 4 for Adaptive Intermediate Representations for Video Understanding
Viaarxiv icon