Imran Razzak
Portrait

Imran Razzak

Associate Professor, Computational Biology
MBZUAI · Abu Dhabi, UAE
CEO, MedOS
MedOS · AI for medicine

About Me

I am an Associate Professor of Computational Biology at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where I lead the GenMI research lab. I am also CEO of MedOS, where we build AI for medicine. Previously, I worked in human-centered machine learning at UNSW and computer science at Deakin University.

My research connects personalized medicine, medical imaging, and multimodal clinical AI. I develop models that bring together imaging, language, and other biomedical data for clinical reasoning and spatial grounding, with an emphasis on robust, trustworthy systems and longitudinal healthcare.

Open positions: I welcome prospective PhD students, postdoctoral researchers, visiting students, and remote interns interested in medical foundation models and clinical reasoning. Please read the application guidance and email your CV and a short research proposal.

MedOS · AI for medicine

Chief Executive Officer

I lead MedOS, a company developing AI tools for clinical care, medical research, and healthcare workflows. Our work connects researchers, engineers, and clinicians to bring medical AI into practice.

Clinical AI
Decision support and diagnostic assistance
Research tools
Evidence synthesis and biomedical discovery
Workflow automation
Documentation, intake, and clinical operations
Visit MedOS MedOS on LinkedIn
Education
  • University of Technology Sydney
    Ph.D. in Machine Learning
  • Deakin University
    Graduate Certificate of Higher Education (Learning and Teaching)
Experience
  • MBZUAI
    Associate Professor, Computational Biology
    Present
  • MedOS
    Chief Executive Officer
    Present
  • UNSW, Sydney
    Human-Centered Machine Learning
  • Deakin University
    Senior Lecturer, Computer Science
Honors & Awards
  • IEEE Andrew P. Sage Transactions Paper Award
    2022
  • IEEE MDM Best Demo Award
    2022
  • MICCAI CuRIOUS Challenge — 1st place
    2022
News
2026
Eight papers accepted at EMNLP: four main-conference papers and four Findings papers.
Aug
Two papers accepted at CIKM.
Jul
Eight papers accepted at MICCAI.
May
Three papers on federated learning accepted at ICML.
May
Two papers on retrieval-augmented generation accepted at ACL: TAGS and Long Context Modeling with Ranked Memory-Augmented Retrieval.
Apr
Our paper on oral microbiome associations with metabolic health accepted in Nature Communications.
Apr
Apr
Four papers accepted at CVPR, including MedMO, LATA (oral), and CHIPS.
Mar
Introducing MedMO: a generalist medical foundation model for multimodal understanding, clinical reasoning, and spatial grounding. Explore the models.
Feb

Recent Publications

2025–2026 highlights · CVPR, ICLR and Nature Communications

Population-scale characterization of the oral microbiome and associations with metabolic health

H Xue, A Godneva, F Tang, H Li, Y Li, M Hu, R Li, J Su, E Segal, I Razzak

Nature Communications · 2026

[Google Scholar]

CARL: Preserving Causal Structure in Representation Learning

Y Li, X Liu, F Tang, Z Lu, M Hu, Y Li, H Xue, P Guo, J Su, Y Xie, E Segal, ...

ICLR · 2026

[Google Scholar]

Figure 1 from CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection Figure 1 · source paper

CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection

Xinlin Zhuang, Yichen Li, Xiwei Liu, Haolin Yang, Yifan Lu, Ziyun Zou, Yulong Li, Huifa Li, Dongliang Chen, Qinglei Wang, Weiyang Liu, Ying Qian, Jiangming Shi, Imran Razzak

CVPR · 2026

[Google Scholar] [Paper] [arXiv]

Figure 2 from Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data Figure 2 · source paper

Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data

Xinlin Zhuang, Feilong Tang, Haolin Yang, Xiwei Liu, Ming Hu, Huifa Li, Haochen Xue, Junjun He, Zongyuan Ge, Yichen Li, Ying Qian, Imran Razzak

CVPR · 2026

[Google Scholar] [Paper] [arXiv]

Figure 4 from Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Figure 4 · source paper

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

Feilong Tang, Chengzhi Liu, Zhongxing Xu, Ming Hu, Zelin Peng, Zhiwei Yang, Jionglong Su, Minquan Lin, Yifan Peng, Xuelian Cheng, Imran Razzak, Zongyuan Ge

CVPR · 2025

[Google Scholar] [Paper] [arXiv]

All publications