PeopleofSuperintelligence

Researcher

Mohamed Elhoseiny

Mohamed Elhoseiny is a computer scientist whose research covers computer vision, vision-language models and AI that generates art and fashion. After studying computer systems at Ain Shams University in Egypt, he finished a Ph.D. at Rutgers University under Ahmed Elgammal in 2016 and spent December 2016 to January 2019 as a postdoctoral researcher at Facebook AI Research. During those years, he coauthored CAN: Creative Adversarial Networks in 2017 and DesIGN: Design Inspiration from Generative Networks, which won the Best Paper Award at the 2018 ECCV Workshop on Fashion, Art, and Design. He joined KAUST in 2019, became a senior member of AAAI in February 2023, and coauthored the vision-language models MiniGPT-4 and MiniGPT-v2 in 2023. Today he is an associate professor of computer science at KAUST and principal investigator of its Vision-CAIR research group.

Badges

Timeline

  1. 2006–2016

    Ain Shams and a Rutgers doctorate

    He earns a B.Sc. in 2006 and an M.S. in 2010, both in computer systems, at Ain Shams University in Egypt. During his Rutgers University doctorate, he receives an NSF Fellowship in 2014 for his Write-a-Classifier project and the Doctoral Consortium Award at CVPR in 2016. He completes the Ph.D. under Ahmed Elgammal in October 2016.

  2. 2016–2019

    Postdoc at Facebook AI Research

    He is a postdoctoral researcher at Facebook AI Research from December 2016 to January 2019. In 2017, he coauthors CAN: Creative Adversarial Networks with Ahmed Elgammal, Bingchen Liu and Marian Mazzone, a modified generative adversarial network that makes art by deviating from learned styles. In tests, human subjects cannot distinguish its images from art by contemporary artists shown in top art fairs.

  3. 2018

    Best paper for DesIGN

    In 2018, he coauthors DesIGN: Design Inspiration from Generative Networks with Othman Sbai, Antoine Bordes, Yann LeCun and Camille Couprie, which tests GAN models and loss functions that boost novelty in fashion generation. The paper wins the Best Paper Award at the ECCV 2018 Workshop on Fashion, Art, and Design. He also presents his zero-shot learning research on AI for biodiversity at the 2018 United Nations Biodiversity Conference in Sharm El Sheikh, Egypt.

  4. 2019

    Assistant professor at KAUST

    In 2019, he joins KAUST's CEMSE Division as an assistant professor of computer science in the Visual Computing Center and becomes principal investigator of the Vision-CAIR research group. He also works as an AI research consultant for Baidu Research's Silicon Valley AI Lab and as a visiting faculty member in Stanford's Computer Science department from 2019 to 2020.

  5. February 2023

    A senior member of AAAI

    In February 2023, he is inducted as a senior member of the Association for the Advancement of Artificial Intelligence at the AAAI-23 awards ceremony in Washington, D.C. He is recognized for his longstanding contributions to AI and long-term AAAI membership.

  6. 2023

    MiniGPT-4 and MiniGPT-v2

    In April 2023, he coauthors MiniGPT-4 with Deyao Zhu, Jun Chen, Xiaoqian Shen and Xiang Li, which aligns a frozen visual encoder with the frozen language model Vicuna through one projection layer; the code, pretrained model and dataset are released. In October 2023, he coauthors MiniGPT-v2, a unified interface for vision-language tasks such as image description, visual question answering and visual grounding.

  7. 2024

    IEEE senior member and SAAI

    He becomes an IEEE Senior Member in 2024 and serves as program chair and co-founder of the SAAI Initiative, an Art & AI symposium and multi-stage hackathon. In May 2024, his multimodal LLM hack HomeGPT takes third place at the Data+AI Summit hackathon in San Francisco.

  8. As of October 2026

    Associate professor at KAUST

    He is an associate professor in the Computer Science Program at KAUST and principal investigator of the KAUST Vision-CAIR Research Group. His research focuses on affective AI that understands and generates novel visual content such as art and fashion, with computer vision, efficient multimodal learning with limited data, and vision and language as primary interests.

Career

  1. Since 2019King Abdullah University of Science and TechnologyAssistant Professor
  2. From 2019BaiduAI research consultant
  3. 2019–2020Stanford UniversityVisiting faculty member
  4. 2016–2019FAIR (Meta)Postdoctoral researcher

Education

  1. 2016Rutgers UniversityPh.D.
  2. 2010Ain Shams UniversityM.S.
  3. 2006Ain Shams UniversityB.Sc.

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Mohamed Elhoseiny. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Mohamed Elhoseiny. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  3. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Mohamed Elhoseiny. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.
  4. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Stanford University. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Mohamed Elhoseiny yet. Send us a free-licensed photo.

  1. Mohamed Elhoseiny | Associate Professor, Computer Science | Computer, Electrical and Mathematical Sciences and Engineering cemse.kaust.edu.sa. Checked 21 October 2026.
  2. Bio and Education - Mohamed H. Elhoseiny mohamed-elhoseiny.com. Checked 21 October 2026.
  3. CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms arxiv.org. Checked 21 October 2026.
  4. DesIGN: Design Inspiration from Generative Networks (ECCV 2018 Workshops open access) openaccess.thecvf.com. Checked 21 October 2026.
  5. CEMSE New Faculty: Mohamed Elhoseiny, Assistant Professor of Computer Science cemse.kaust.edu.sa. Checked 21 October 2026.
  6. Professor Elhoseiny elected as a Senior Member of the Association for the Advancement of Artificial Intelligence cemse.kaust.edu.sa. Checked 21 October 2026.
  7. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models arxiv.org. Checked 21 October 2026.
  8. MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning arxiv.org. Checked 21 October 2026.