José Lezama · Research Scientist

Staff Research Scientist at Google Deepmind. Working on modeling the visual world: VideoPoet, WALT, Veo2, Veo3.

Recent publications

Photorealistic Video Generation with Diffusion Models (W.A.L.T.)
A Gupta, L Yu, K Sohn, X Gu, M Hahn, FF Li, I Essa, L Jiang, J Lezama
ECCV 2024 (Project Page)
VideoPoet: A Large Language Model for Zero-Shot Video Generation
D Kondratyuk, L Yu, X Gu, J Lezama, J Huang et al.
ICML 2024 Best Paper Award (Project Page)
MaskSketch: Unpaired Structure-guided Masked Image Generation
Bashkirova, D., Lezama, J., Sohn, K., Saenko, K. and Essa, I.,
CVPR 2023 Highlight (Project Page)
MAGVIT: Masked Generative Video Transformer
Yu, L., Cheng, Y., Sohn, K., Lezama, J., Zhang, H., Chang, H., Hauptmann, A.G., Yang, M.H., Hao, Y., Essa, I. and Jiang, L.,
CVPR 2023 Highlight (Article)
Visual Prompt Tuning for Generative Transfer Learning
Sohn, K., Hao, Y., Lezama, J., Polania, L., Chang, H., Zhang, H., Essa, I. and Jiang, L.,
CVPR 2023 (Article)
MUSE: Text-To-Image Generation via Masked Generative Transformers
Chang, H., Zhang, H., Barber, J., Maschinot, A.J., Lezama, J., Jiang, L., Yang, M.H., Murphy, K., Freeman, W.T., Rubinstein, M. and Li, Y.
Arxiv 2023 (Article)
Discrete Predictor-Corrector Diffusion Models for Image Synthesis
José Lezama, Tim Salimans, Lu Jiang, Huiwen Chang, Jonathan Ho, Irfan Essa
ICLR 2023 (Article)
Improved Masked Image Generation with Token-Critic
José Lezama, Huiwen Chang, Lu Jiang, Irfan Essa
ECCV 2022 (Article)
Old academic website

MsC, PhD, Ecole Normale Supérieure Paris-Saclay, France (ex ENS Cachan). Advisors: Jean-Michel Morel, Gregory Randall
BSc, Universidad de la República, Uruguay

I received outstanding reviewer mentions at CVPR 2019, ECCV 2020, NeurIPS 2020, ICLR 2021, NeurIPS 2022.
I help with the organization of the Latin American Meeting in AI, Khipu.ai.