Mark Ibrahim

SOFTWARE ENGINEER | NEW YORK CITY, UNITED STATES

How do we encode our intuitive ability to recognize the same dog while it's jumping during the day or hiding behind a tree at night? Mark is interested in building representations of the factors of variation in the world around us. Mark is exploring how tools from areas such as topology, group theory, and equivariant architectures can shed light on how representations can improve interpretability, robustness, and data-efficiency (semi- or self-supervised settings).

Research Areas

Computer Vision

Core Machine Learning

Mark's Work

Building AI that can understand variation in the world around us

Addressing the Topological Defects of Disentanglement via Distributed Operators

Mark's Publications

June 05, 2024

CORE MACHINE LEARNING

An Introduction to Vision-Language Modeling

Florian Bordes, Richard Pang, Anurag Ajay, Alexander C. Li, Adrien Bardes, Suzanne Petryk, Oscar Mañas, Zhiqiu Lin, Anas Mahmoud, Bargav Jayaraman, Mark Ibrahim, Melissa Hall, Yunyang Xiong, Jonathan Lebensold, Candace Ross, Srihari Jayakumar, Chuan Guo, Diane Bouchacourt, Haider Al-Tahan, Karthik Padthe, Vasu Sharma, Hu Xu, Ellen Tan, Megan Richards, Samuel Lavoie, Pietro Astolfi, Reyhane Askari, Jun Chen, Kushal Tirumala, Rim Assouel, Mazda Moayeri, Arjang Talattof, Kamalika Chaudhuri, Zechun Liu, Xilun Chen, Quentin Garrido, Karen Ullrich, Aishwarya Agrawal, Kate Saenko, Asli Celikyilmaz, Vikas Chandra