Mitesh Kumar Singh


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.

Research Areas

Mitesh's Work

Mitesh's Publications

September 27, 2023


Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

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

September 27, 2023