Mitesh is a Software Engineer at Facebook AI Applied Research. His interests lie at the intersection of computer vision and natural language processing. Since joining Facebook in early 2020, he has worked on multimodal video content understanding (audio, visual and text) and classification, with a focus on building low compute video models and deploying video research to production at scale.
Prior to Facebook, Mitesh graduated with a Master's in Computer Science from Stony Brook University, where he broadly focused on machine learning and AI and specifically on building open domain, contextual and conversational question answering systems.

September 27, 2023
Ji Hou, Abhimanyu Dubey, Abhishek Kadian, Devi Parikh, Dhruv Mahajan, Filip Radenovic, Jialiang Wang, Kevin Chih-Yao Ma, Kunpeng Li, Matthew Yu, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Roshan Sumbaly, Rui Wang, Sam Tsai, Simon Vandenhende, Simran Motwani, Vignesh Ramanathan, Vladan Petrovic, Xiaofang Wang, Xiaoliang Dai, Yi Wen, Yiwen Song, Yue (R) Zhao, Zijian He
September 27, 2023
Our approach
Latest news
Foundational models