Rohit Girdhar
RESEARCH SCIENTIST | NEW YORK CITY, UNITED STATES
Rohit is a research scientist at Facebook AI Research (FAIR) working on computer vision and machine learning. His current research focuses on modeling temporal dynamics, with applications including video understanding and physical reasoning. He earned his PhD from Carnegie Mellon University, where he studied learning based methods to understand people in images and videos.
Rohit's Publications
July 29, 2024
COMPUTER VISION
CORE MACHINE LEARNING
Factorizing Text-to-Video Generation by Explicit Image Conditioning
Mian Akbar Shah, Devi Parikh, Samaneh Azadi, Andrew Brown, Ishan Misra, Mannat Singh, Quentin Duval, Rohit Girdhar, Saketh Rambhatla, Xi Yin
July 29, 2024
April 23, 2024
CONVERSATIONAL AI
GRAPHICS
Generating Illustrated Instructions
Rohit Girdhar, Ishan Misra, Sachit Menon
April 23, 2024
October 02, 2023
COMPUTER VISION
The effectiveness of MAE pre-pretraining for billion-scale pretraining
Mannat Singh, Aaron Adcock, Christoph Feichtenhofer, Haoqi Fan, Ishan Misra, Piotr Dollar, Quentin Duval, Rohit Girdhar, Ross Girshick, Vaibhav Aggarwal
October 02, 2023
May 09, 2023
COMPUTER VISION
ImageBind: One Embedding Space To Bind Them All
Ishan Misra, Alaa El-Nouby, Armand Joulin, Kalyan Vasudev Alwala, Mannat Singh, Rohit Girdhar, Zhuang Liu
May 09, 2023
July 26, 2022
RESEARCH
COMPUTER VISION
Detecting Twenty-thousand Classes using Image-level Supervision
Ishan Misra, Armand Joulin, Rohit Girdhar, Xingyi Zhou, Phillip Krahenbuhl
July 26, 2022
July 07, 2022
Omnivore: A Single Model for Many Visual Modalities
Ishan Misra, Armand Joulin, Laurens van der Maaten, Mannat Singh, Nikhila Ravi, Rohit Girdhar
July 07, 2022
Our approach
Latest news
Foundational models
Meta © 2026