Bahjat Kawar

Ph.D. in computer science from Technion. Computer vision researcher at Apple.
Researching machine learning & computer vision. Interested in diffusion models.
LinkedIn  -  GitHub  -  Twitter  -  Google Scholar  -  Semantic Scholar




About Me

I am a senior computer vision researcher at Apple in Herzliya. I recently graduated with a Ph.D. in computer science from Technion, researching computer vision and machine learning under the supervision of Prof. Michael Elad. I am interested in inverse problems, generative models, representation learning, and diffusion models. I have also spent the 2022 summer as a research intern at Google Research in Tel Aviv.

Prior to my Ph.D. studies, I obtained my B.Sc. in computer science from Technion, summa cum laude, as the class valedictorian. I also worked as a research intern at Cornell Tech in New York City, and as a freelance web and app developer.


Publications

2024

Beomsu Kim, Yu-Guan Hsieh, Michal Klein, Marco Cuturi, Jong Chul Ye, Bahjat Kawar, James Thornton
Simple ReFlow: Improved Techniques for Fast Flow Models
Preprint, arXiv:2410.07815.

Bahjat Kawar*, Noam Elata*, Tomer Michaeli, Michael Elad
GSURE-Based Diffusion Model Training with Corrupted Data
TMLR 2024, in Transactions on Machine Learning Research.
[code]

Noam Elata, Bahjat Kawar, Tomer Michaeli, Michael Elad
Nested Diffusion Processes for Anytime Image Generation
WACV 2024, in The IEEE/CVF Winter Conference on Applications of Computer Vision.
[code]

2023

Hadas Orgad*, Bahjat Kawar*, Yonatan Belinkov
Editing Implicit Assumptions in Text-to-Image Diffusion Models
ICCV 2023, in The IEEE/CVF International Conference on Computer Vision.
[website]  [code]

Roy Ganz, Bahjat Kawar, Michael Elad
Do Perceptually Aligned Gradients Imply Adversarial Robustness?
ICML 2023 oral presentation, in International Conference on Machine Learning.

Bahjat Kawar*, Shiran Zada*, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, Michal Irani
Imagic: Text-Based Real Image Editing with Diffusion Models
CVPR 2023, in The IEEE/CVF Conference on Computer Vision and Pattern Recognition.
[website]

Bahjat Kawar, Roy Ganz, Michael Elad
Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
TMLR 2023, in Transactions on Machine Learning Research.
[code]

Michael Elad, Bahjat Kawar, Gregory Vaksman
Image Denoising: The Deep Learning Revolution and Beyond —A Survey Paper—
SIIMS 2023, in SIAM Journal on Imaging Sciences.

2022

Bahjat Kawar*, Jiaming Song*, Stefano Ermon, Michael Elad
JPEG Artifact Correction using Denoising Diffusion Restoration Models
NeurIPSW 2022, in NeurIPS Workshop on Score-Based Methods.
[code]

Bahjat Kawar, Michael Elad, Stefano Ermon, Jiaming Song
Denoising Diffusion Restoration Models
NeurIPS 2022, in Advances in Neural Information Processing Systems.
[website]  [code]

Tsachi Blau, Roy Ganz, Bahjat Kawar, Alex Bronstein, Michael Elad
Threat Model-Agnostic Adversarial Defense using Diffusion Models
Preprint, arXiv:2207.08089.

2021

Bahjat Kawar, Gregory Vaksman, Michael Elad
SNIPS: Solving Noisy Inverse Problems Stochastically
NeurIPS 2021, in Advances in Neural Information Processing Systems.
[code]

Bahjat Kawar, Gregory Vaksman, Michael Elad
Stochastic Image Denoising by Sampling from the Posterior Distribution
ICCVW 2021, in ICCV Workshop on Advances in Image Manipulation.


Awards

I am a recipient of the following awards:
  • Technion MLIS-TCE Best Paper Award 2022
  • Council for Higher Education VATAT Scholarship 2021
  • Apple Excellence Award 2019
  • Ernest Freudman Fellowship 2018
  • LAPIDIM Excellence Program 2018-2020
  • Technion President's List Award for Excellence (6×) 2017-2020
I have served as a reviewer / program committee member at the following venues:
  • NeurIPS 2021, 2022, 2023
  • ICML 2022
  • AAAI 2023
  • CVPR 2023
  • ICCV 2023
  • TMLR 2023
  • Workshops at ICCV 2021, ICLR 2022, ICML 2022, ICML 2023
  • IEEE Transactions on Computational Imaging 2022
I was also a co-organizer of the NeurIPS 2023 Workshop on Diffusion Models.

Teaching

I teach / have taught the following courses as a TA:
  • Generative AI - Diffusion Models (236610) – Winter 2022-2023
  • Project in Image Processing (234329) – Winter 2021-2022
  • Operating Systems (234123) – Spring 2020, Winter 2020-2021, Spring 2021
  • Logic Design (234262) – Winter 2018-2019