Roshan Sumbaly
DIRECTOR OF AI, LLAMA | MENLO PARK, UNITED STATES
Roshan Sumbaly leads the Llama Applied Research group responsible for post-training & democratization of Llama / Emu foundation models internally and externally. Before that he led various applied research teams ranging from vision tasks for integrity efforts to multi-modal ones for our AR investment. Before Meta, he led leadership roles at Coursera and LinkedIn, working on recommendation systems and data products.
Research Areas
Roshan's Work
Roshan's Publications
July 23, 2024
COMPUTER VISION
Imagine yourself: Tuning-Free Personalized Image Generation
Zecheng He, Bo Sun, Felix Xu, Haoyu Ma, Ankit Ramchandani, Vincent Cheung, Siddharth Shah, Anmol Kalia, Ning Zhang, Peizhao Zhang, Roshan Sumbaly, Peter Vajda, Animesh Sinha
July 23, 2024
April 18, 2024
COMPUTER VISION
Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation
Jonas Kohler, Albert Pumarola, Edgar Schoenfeld, Artsiom Sanakoyeu, Roshan Sumbaly, Peter Vajda, Ali Thabet
April 18, 2024
September 27, 2023
COMPUTER VISION
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
Foundational models
Latest news
Foundational models
Meta © 2024