Alert button
Picture for Thomas Kollar

Thomas Kollar

Alert button

Toyota Research Institute

Linearizing Large Language Models

Add code
Bookmark button
Alert button
May 10, 2024
Jean Mercat, Igor Vasiljevic, Sedrick Keh, Kushal Arora, Achal Dave, Adrien Gaidon, Thomas Kollar

Viaarxiv icon

How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation

Add code
Bookmark button
Alert button
May 08, 2024
Joseph A. Vincent, Haruki Nishimura, Masha Itkina, Paarth Shah, Mac Schwager, Thomas Kollar

Viaarxiv icon

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

Add code
Bookmark button
Alert button
Mar 19, 2024
Alexander Khazatsky, Karl Pertsch, Suraj Nair, Ashwin Balakrishna, Sudeep Dasari, Siddharth Karamcheti, Soroush Nasiriany, Mohan Kumar Srirama, Lawrence Yunliang Chen, Kirsty Ellis, Peter David Fagan, Joey Hejna, Masha Itkina, Marion Lepert, Yecheng Jason Ma, Patrick Tree Miller, Jimmy Wu, Suneel Belkhale, Shivin Dass, Huy Ha, Arhan Jain, Abraham Lee, Youngwoon Lee, Marius Memmel, Sungjae Park, Ilija Radosavovic, Kaiyuan Wang, Albert Zhan, Kevin Black, Cheng Chi, Kyle Beltran Hatch, Shan Lin, Jingpei Lu, Jean Mercat, Abdul Rehman, Pannag R Sanketi, Archit Sharma, Cody Simpson, Quan Vuong, Homer Rich Walke, Blake Wulfe, Ted Xiao, Jonathan Heewon Yang, Arefeh Yavary, Tony Z. Zhao, Christopher Agia, Rohan Baijal, Mateo Guaman Castro, Daphne Chen, Qiuyu Chen, Trinity Chung, Jaimyn Drake, Ethan Paul Foster, Jensen Gao, David Antonio Herrera, Minho Heo, Kyle Hsu, Jiaheng Hu, Donovon Jackson, Charlotte Le, Yunshuang Li, Kevin Lin, Roy Lin, Zehan Ma, Abhiram Maddukuri, Suvir Mirchandani, Daniel Morton, Tony Nguyen, Abigail O'Neill, Rosario Scalise, Derick Seale, Victor Son, Stephen Tian, Emi Tran, Andrew E. Wang, Yilin Wu, Annie Xie, Jingyun Yang, Patrick Yin, Yunchu Zhang, Osbert Bastani, Glen Berseth, Jeannette Bohg, Ken Goldberg, Abhinav Gupta, Abhishek Gupta, Dinesh Jayaraman, Joseph J Lim, Jitendra Malik, Roberto Martín-Martín, Subramanian Ramamoorthy, Dorsa Sadigh, Shuran Song, Jiajun Wu, Michael C. Yip, Yuke Zhu, Thomas Kollar, Sergey Levine, Chelsea Finn

Figure 1 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Figure 2 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Figure 3 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Figure 4 for DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Viaarxiv icon

Language models scale reliably with over-training and on downstream tasks

Add code
Bookmark button
Alert button
Mar 13, 2024
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Jenia Jitsev, Alexandros G. Dimakis, Gabriel Ilharco, Shuran Song, Thomas Kollar, Yair Carmon, Achal Dave, Reinhard Heckel, Niklas Muennighoff, Ludwig Schmidt

Figure 1 for Language models scale reliably with over-training and on downstream tasks
Figure 2 for Language models scale reliably with over-training and on downstream tasks
Figure 3 for Language models scale reliably with over-training and on downstream tasks
Figure 4 for Language models scale reliably with over-training and on downstream tasks
Viaarxiv icon

A Critical Evaluation of AI Feedback for Aligning Large Language Models

Add code
Bookmark button
Alert button
Feb 19, 2024
Archit Sharma, Sedrick Keh, Eric Mitchell, Chelsea Finn, Kushal Arora, Thomas Kollar

Viaarxiv icon

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Add code
Bookmark button
Alert button
Feb 12, 2024
Siddharth Karamcheti, Suraj Nair, Ashwin Balakrishna, Percy Liang, Thomas Kollar, Dorsa Sadigh

Figure 1 for Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Figure 2 for Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Figure 3 for Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Figure 4 for Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Viaarxiv icon

The Teenager's Problem: Efficient Garment Decluttering With Grasp Optimization

Add code
Bookmark button
Alert button
Oct 25, 2023
Aviv Adler, Ayah Ahmad, Shengyin Wang, Wisdom C. Agboh, Edith Llontop, Tianshuang Qiu, Jeffrey Ichnowski, Mehmet Dogar, Thomas Kollar, Richard Cheng, Ken Goldberg

Viaarxiv icon

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

Add code
Bookmark button
Alert button
Aug 24, 2023
Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu, Vitor Guizilini, Thomas Kollar, Adrien Gaidon, Zsolt Kira, Rares Ambrus

Figure 1 for NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Figure 2 for NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Figure 3 for NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Figure 4 for NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Viaarxiv icon

Bagging by Learning to Singulate Layers Using Interactive Perception

Add code
Bookmark button
Alert button
Mar 29, 2023
Lawrence Yunliang Chen, Baiyu Shi, Roy Lin, Daniel Seita, Ayah Ahmad, Richard Cheng, Thomas Kollar, David Held, Ken Goldberg

Figure 1 for Bagging by Learning to Singulate Layers Using Interactive Perception
Figure 2 for Bagging by Learning to Singulate Layers Using Interactive Perception
Figure 3 for Bagging by Learning to Singulate Layers Using Interactive Perception
Figure 4 for Bagging by Learning to Singulate Layers Using Interactive Perception
Viaarxiv icon

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Add code
Bookmark button
Alert button
Mar 28, 2023
Nick Heppert, Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu, Rares Andrei Ambrus, Jeannette Bohg, Abhinav Valada, Thomas Kollar

Figure 1 for CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
Figure 2 for CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
Figure 3 for CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
Figure 4 for CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
Viaarxiv icon