Ron Mokady

I’m the Director of Research at BRIA AI, leading the training of visual generative AI models using licensed data.

Previously, I was a Computer Science Ph.D. student at Tel-Aviv University, under the supervision of Prof. Daniel Cohen-Or and Dr. Amit H. Bermano.

During that time, I spent the 2020 summer at FAIR under the supervision of Prof. Lior Wolf, and the 2021 and 2022 summers at Google.

My main research interest is machine learning applications for computer vision and graphics. In particular, I work on image and video synthesis, while also interested in disentanglement, temporal coherence, supervision reduction, and the utilization of pre-trained models.

Email  /  Github  /  LinkedIn  /  Semantic Scholar  /  Twitter

Ron Mokady
Publications
NULL-text Inversion for Editing Real Images using Guided Diffusion Models
Ron Mokady*, Amir Hertz*, Kfir Aberman, Yael Pritch, Daniel Cohen-Or,
(* denotes equal contribution)
CVPR, 2023.
project page / code / arXiv



Prompt-to-Prompt Image Editing with Cross Attention Control
Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, Daniel Cohen-Or
ICLR, 2023.
project page / code / paper arXiv



Text-Only Training for Image Captioning using Noise-Injected CLIP
David Nukrai, Ron Mokady, Amir Globerson
Findings of EMNLP, 2022.
arXiv



Self-Distilled StyleGAN: Towards Generation from Internet Photos
Ron Mokady, Michal Yarom, Omer Tov, Oran Lang, Daniel Cohen-Or, Tali Dekel, Michal Irani, Inbar Mosseri
SIGGRAPH, 2022.
project page / arXiv / Supplementary / Datasets and Models



Stitch it in Time: GAN-Based Facial Editing of Real Videos
Rotem Tzaban, Ron Mokady, Rinon Gal, Amit H. Bermano, Daniel Cohen-Or
SIGGRAPH ASIA, 2022.
project page / arXiv / code



State-of-the-Art in the Architecture, Methods and Applications of StyleGAN
Amit H. Bermano, Rinon Gal, Yuval Alaluf, Ron Mokady, Yotam Nitzan, Omer Tov, Or Patashnik, Daniel Cohen-Or
EUROGRAPHICS (STAR), 2022.
arXiv



ClipCap: CLIP Prefix for Image Captioning
Ron Mokady, Amir Hertz, Amit H. Bermano,
arXiv, 2021.
arXiv / code

HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing
Yuval Alaluf*, Omer Tov*, Ron Mokady, Rinon Gal, Amit H. Bermano,
CVPR, 2022.
project page / arXiv / code



Pivotal Tuning for Latent-based Editing of Real Images
Daniel Roich, Ron Mokady, Amit H. Bermano, Daniel Cohen-Or
Transactions On Graphics, 2022.
arXiv / TOG / code
JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
Ron Mokady, Rotem Tzaban, Sagie Benaim, Amit H. Bermano, Daniel Cohen-Or
Computer Graphics Forum, 2022.
project page / arXiv / code

Structural-analogy from a Single Image Pair
Sagie Benaim*, Ron Mokday*, Amit H. Bermano, Daniel Cohen-Or, Lior Wolf
(* denotes equal contribution)
Computer Graphics Forum, 2020.
Also in the Deep Internal Learning workshop, ECCV 2020.
project page / arXiv / code / video
Masked Based Unsupervised Content Transfer
Ron Mokday, Sagie Benaim, Amit H. Bermano, Lior Wolf
ICLR, 2020.  
paper / code / video



Talks
Prompt-To-Prompt Editing with Diffusion Models. Israeli Computer Vision Day 2023. Video

Moving forward with StyleGAN to Real Data and New Domains. TAU Visual Computing Seminar, Technion Pixel Club, Weizmann Institute seminar, 2022. PDF

Deep Video Synthesis. PKU VCL Seminar, 2020. PDF

Mask Based Unsupervised Content Transfer. Alibaba's Deep academy, 2020. Video (Hebrew)

Image Generation Using Disentanglement. Tel-Aviv University Visual Computing Seminar, 2019. PDF

Teaching
Workshop in Machine Learning Applications for Computer Graphics (2019/20) @ TAU
Workshop On Image Processing Based On Deep Networks (2020/21) @ TAU


This page design is based on a template by Jon Barron.