Motasem Alfarra

Motasem Alfarra

PhD Candidate - Electrical and Computer Engineering



I am a Ph.D. candidate at KAUST in Saudi Arabia. I am part of the Image and Video Understanding Lab (IVUL) advised by Prof. Bernard Ghanem. I obtained my M.Sc degree in Electrical Engineering from KAUST, and my undergraduate degree in Electrical Engineering from Kuwait University. I am interested in test-time adaptation and continual learning. Previously, I worked on assessing and enhancing network robustness and leveraging robust models for different applications.

Download my resumé.

  • Test Time Adaptation
  • Continual Learning
  • Adversarial Robustness
  • Computer Vision and Machine Learning
  • PhD in Electrical and Computer Engineering, 2020-Present


  • MSc in Electrical Engineering, 2019-2020


  • BSc in Electrical Engineering, 2014-2018

    Kuwait University


Qualcomm AI Research
Research Internship
May 2023 – Sep 2023 Amsterdam, Netherlands
Research internship at the federated learning team in Qualcomm AI Research.
Research Internship
Aug 2022 – Jan 2023 Münich, Germany
Research internship at the Embodied AI Lab at Intel supervised by Matthias Müller.
University of Oxford
Research Internship
Oct 2021 – Feb 2022 Oxford, United Kingdom
Research visit to the Torr Vision Group (TVG) supervised by Prof. Philip Torr.
Teacher Assistant
Jan 2021 – May 2021 Saudi Arabia
I was a TA for the Ph.D course “Introduction to Computer Vision”.
Universidad Panamericana
Guest Lecturer
Jul 2020 – Jul 2020 Mexico
I gave one lecture titled “Adversarial Attacks and Network Robustness”.
Kuwait University
Research Assistant
Jul 2017 – May 2018 Kuwait
Developed algorithms and implemented network simulations.

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). Generalizability of Adversarial Robustness Under Distribution Shifts. In TMLR [Featured].

PDF Cite

(2023). Online Distillation with Continual Learning for Cyclic Domain Shifts. In CVPRW'23.

PDF Cite Code

(2023). Towards Assessing and Characterizing the Semantic Robustness of Face Recognition. In CVPRW'23.

PDF Cite

(2023). PIVOT: Prompting for Video Continual Learning. In CVPR'23.

PDF Cite

(2023). Real-Time Evaluation in Online Continual Learning: A New Hope. In CVPR'23.

PDF Cite Code Poster