Yaniv Taigman
RESEARCH SCIENTIST | MENLO PARK, UNITED STATES
Yaniv Taigman graduated from Tel-Aviv University with a Master's in Computer Science. While pursuing his PhD research, he co-founded Face.com where he held the position of CTO. When Face.com was acquired by Facebook in 2012, Yaniv joined the office in Menlo Park to lead research and engineering projects. During this time he worked on efficient methods for face representation (DeepFace project) with colleagues, and helped start the Facebook AI Research (FAIR) group. In 2016, he established a satellite FAIR team in Tel-Aviv.
Yaniv's Publications
March 30, 2025
COMPUTER VISION
Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation
Sagie Benaim, Adam Polyak, Amit Zohar, Guy Yariv, Shelly Sheynin, Yaniv Taigman, Yossef (Yossi) Adi, Yuval Kirstain
March 30, 2025
September 10, 2024
COMPUTER VISION
Video Editing via Factorized Diffusion Distillation
Uriel Singer, Adam Polyak, Amit Zohar, Devi Parikh, Shelly Sheynin, Yaniv Taigman, Yuval Kirstain
September 10, 2024
July 14, 2023
NLP
COMPUTER VISION
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
Armen Aghajanyan, Adam Polyak, Arun Babu, Asli Celikyilmaz, Benjamin Miller, Binh Tang, Bowen Shi, Brian Karrer, Candace Ross, Daniel Li (FAIR), Gargi Ghosh, Jacob Xu, Lili Yu, Luke Zettlemoyer, Maryam Fazel-Zarandi, Olga Golovneva, Ram Pasunuru, Russ Howes, Shelly Sheynin, Tianlu Wang, Uriel Singer, Vasu Sharma, Yaniv Taigman
July 14, 2023
July 26, 2022
Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
Oran Gafni, Adam Polyak, Devi Parikh, Oron Ashual, Shelly Sheynin, Yaniv Taigman
July 26, 2022
August 02, 2020
August 02, 2020
August 13, 2018
RESEARCH
COMPUTER VISION
Unsupervised Generation of Free-Form and Parameterized Avatars
Adam Polyak, Lior Wolf, Yaniv Taigman
August 13, 2018
July 11, 2018
RESEARCH
SPEECH & AUDIO
Fitting New Speakers Based on a Short Untranscribed Sample
Eliya Nachmani, Adam Polyak, Lior Wolf, Yaniv Taigman
July 11, 2018
Our approach
Latest news
Foundational models
Meta © 2026