Taha Koleilat

Montreal, Canada

Hi, I am Taha Koleilat, a PhD candidate in Electrical & Computer Engineering at Concordia University, Montreal. I am a Graduate Research Assistant at the IMPACT and Health-X Labs, supervised by Prof. Hassan Rivaz and Prof. Yiming Xiao.

Previously, I attained my BEng in Computer & Communications Engineering at the American University of Beirut, graduating with High Distinction (4.0/4.0) and a minor in Economics.

My research lies at the intersection of medical image analysis, vision–language models, and foundation models. I focus on developing data-efficient, generalizable, and interpretable multimodal learning frameworks that bridge medical images and clinical text, enabling robust performance under low-data and cross-domain settings.

My work has been published at leading venues including CVPR, MICCAI, and Medical Image Analysis, and has been supported by major competitive awards such as the FRQNT Doctoral Scholarship.

Currently, I am working on text-driven medical image segmentation, vision–language model adaptation, and uncertainty-aware multimodal learning for efficient and reliable clinical deployment.

I am serving as a reviewer for leading venues including IEEE TPAMI, MICCAI, Medical Image Analysis (MedIA), and IEEE TMI.

Email / Google Scholar / GitHub / LinkedIn / CV

News

Oct 5, 2025	Our paper MedViTV2 was accepted to Applied Soft Computing. Congrats to all co-authors!
Jul 30, 2025	Our paper GroundingDINO-US-SAMwas accepted to IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (TUFFC). Congrats to all co-authors!
Jul 22, 2025	Our paper MedCLIP-SAMv2 was accepted to Medical Image Analysis (MedIA). Congrats to all co-authors!
Jul 10, 2025	Our paper TextSAM-EUS was accepted at the CVAMD Workshop (ICCV 2025), see you in Honolulu, Hawaii!
Apr 30, 2025	I was awarded the FRQNT Doctoral Training Scholarship, ranked 2nd province-wide, supporting my research on Vision–Language Models for healthcare.
Mar 15, 2025	I am serving as a reviewer for MICCAI 2025.
Feb 27, 2025	Our paper BiomedCoOp was accepted at CVPR 2025, see you in Nashville, Tennessee!
Jan 25, 2025	I received the Concordia University Doctoral Graduate Fellowship, awarded to exceptional doctoral students for academic and research excellence.

View all news

Selected publications

* denotes joint first authors

2025

Biomedcoop: Learning to prompt for biomedical vision-language models

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, and Yiming Xiao

In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025

Bib PDF Citations Code ★

Website

@inproceedings{koleilat2025biomedcoop,
  title = {Biomedcoop: Learning to prompt for biomedical vision-language models},
  author = {Koleilat, Taha and Asgariandehkordi, Hojat and Rivaz, Hassan and Xiao, Yiming},
  booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages = {14766--14776},
  year = {2025},
}

Medclip-samv2: Towards universal text-driven medical image segmentation

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, and Yiming Xiao

Medical Image Analysis, 2025

Bib PDF Citations Code ★

Website

@article{koleilat2025medclip,
  title = {Medclip-samv2: Towards universal text-driven medical image segmentation},
  author = {Koleilat, Taha and Asgariandehkordi, Hojat and Rivaz, Hassan and Xiao, Yiming},
  journal = {Medical Image Analysis},
  pages = {103749},
  year = {2025},
  publisher = {Elsevier},
}

Textsam-eus: Text prompt learning for sam to accurately segment pancreatic tumor in endoscopic ultrasound

Pascal Spiegler*, Taha Koleilat*, Arash Harirpoush, Corey S Miller, Hassan Rivaz, Marta Kersten-Oertel, and Yiming Xiao

In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Bib PDF Citations Code ★

@inproceedings{spiegler2025textsam,
  title = {Textsam-eus: Text prompt learning for sam to accurately segment pancreatic tumor in endoscopic ultrasound},
  author = {Spiegler*, Pascal and Koleilat*, Taha and Harirpoush, Arash and Miller, Corey S and Rivaz, Hassan and Kersten-Oertel, Marta and Xiao, Yiming},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {948--957},
  year = {2025},
}

2024

Medclip-sam: Bridging text and image towards universal medical image segmentation

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, and Yiming Xiao

In International conference on medical image computing and computer-assisted intervention, 2024

Bib PDF Citations Code ★

Website

@inproceedings{koleilat2024medclip,
  title = {Medclip-sam: Bridging text and image towards universal medical image segmentation},
  author = {Koleilat, Taha and Asgariandehkordi, Hojat and Rivaz, Hassan and Xiao, Yiming},
  booktitle = {International conference on medical image computing and computer-assisted intervention},
  pages = {643--653},
  year = {2024},
  organization = {Springer},
}