🧐 About Me

Hi there! I am a second year PhD. candidate in Computer Vision at the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) under the supervision of Dr. Mohammad Yaqub at BioMedia Lab. I completed my MS in Machine Learning at MBZUAI under the supervision of Dr. Karthik Nandakumar and Dr. Mohammad Yaqub.

Research Interests: I am interested in AI-for-Healthcare and aim to build AI applications that are safe, robust, and deployable for downstream medical tasks. My work bridges model-centric and data-centric approaches to ensure generalizability and trust in clinical environments. Specifically:

• Efficiency: Unsupervised Adaptation, Distillation
• Trustworthiness: Adversarial Training, Test-Time Adaptation
• Domain Generalization: Model Merging, Zero-shot Generalization
• Current Focus: Robust Dermatology VLMs, LLM Merging

🤔 I’m currently involved in 3 main projects: Test-time merging on Med-LLMs, A survey on Unsupervised Functions, Low-shot generalization of Dermatology-VLM. Please feel free to contact at raza dot imam at mbzuai dot ac dot ae for collaboration.

🔥 News

📝 Selected Publications

(^* indicates equal contribution; ^# indicates corresponding authorship.)

MIUA 2025, Best Paper

On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?
Raza Imam^#, Rufael Marew, Mohammad Yaqub. (MIUA 2025) code

• TLDR;

  We introduce MediMeta-C (with MedMNIST-C) to benchmark MVLM robustness under real-world corruptions and propose RobustMedCLIP, a lightweight few-shot, low-rank adaptation that significantly restores performance on noisy medical images without sacrificing accuracy on clean data.

ICML 2025, Spotlight

From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents
Mohammad Amaan Sayeed^*, Mohammed Talha Alam^*, Raza Imam^* Shahab Saquib Sohail, Amir Hussain (ICMLxMusiML 2025)

• TLDR;

  We introduce TibbeAG, a pipeline that benchmarks LLaMA-3, Mistral7B, and Qwen2-7B on Prophetic Medicine QA by combining retrieval-augmented generation and agentic self-critique—yielding a 13% boost in factual accuracy and a further 10% gain in mechanistic insight and safety.

ICCV 2025, Poster

Noise is an efficient learner for zero-shot vision-language models
Raza Imam^#, Asif Hanif, Jian Zhang, Khaled Waleed Dawoud, Yova Kementchedjhieva, Mohammad Yaqub. (ICCVxCLVL 2025) code

• TLDR;

  We introduce Test-Time Noise Tuning (TNT), which learns input-space noise and enforces multi-view embedding alignment to adapt vision-language models on unlabeled test samples, yielding +7.38% on natural distribution shifts and +0.80% on cross-dataset benchmarks over zero-shot CLIP.

WACV 2025, Poster

Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
Raza Imam^#, Hanan Ghani, Muhammad Huzaifa, Karthik Nandakumar. (WACV 2025) code

• TLDR;

  Introduces Test-Time Low-rank Adaptation (TTL) as a parameter-efficient alternative to prompt tuning for zero-shot generalization of VLMs. TTL updates transformer attention weights during inference by maximizing prediction confidence using a weighted entropy loss for consistency across augmented samples.

MICCAI 2023, Spotlight

SEDA: Self-ensembling ViT with Defensive Distillation and Adversarial Training for Robust Chest X-Rays Classification
Raza Imam^#, Ibrahim Almakky, Salma Alrashdi, Baketah Alrashdi, Mohammad Yaqub. (MICCAI 2023) code

• TLDR;

  SEDA utilizes efficient CNN blocks to learn spatial features with various levels of abstraction from feature representations extracted from intermediate ViT blocks, that are largely unaffected by adversarial perturbations. SEDA achieves computational efficiency of 70x times lighter framework and enhanced robustness of +9%.

MIUA 2023, Poster

On enhancing the robustness of Vision Transformers: Defensive Diffusion
Raza Imam, Muhammad Huzaifa^#, Mohammed El-Amine Azz. (MIUA 2023) code

• TLDR;

  We introduced a defensive diffusion technique as an adversarial purifier to eliminate adversarial noise introduced by attackers in the original image. Extensive experiments conducted on a publicly available Tuberculosis X-ray dataset validate the computational efficiency and improved robustness achieved by our proposed architecture.

Elsevier JKSU

A systematic literature review of attribute based encryption in health services
Raza Imam, Kaushal Kumar, Syed Mehran Raza, Rumi Sadaf, Faisal Anwer^#, Noor Fatima, Mohammad Nadeem, Mohamed Abbas, Obaidur Rahman. (Elsevier JKSU)

• TLDR;

  A systematic and comprehensive study of ABE works concerning E-Health as the authors rigorously investigate healthcare-focused ABE frameworks. This will help future research in ABE to secure the existing E-Health data sharing more effectively.

🎖 Honors and Awards

• 2025.07 Best Paper Award at 29th MIUA Conference 2025, Leeds, UK
• 2025.07 Oral Paper Presentation at 29th MIUA Conference 2025, Leeds, UK
• 2025.06 Spotlight Presentation at MusiML, 42nd ICML, 2025, Vancouver, Canada
• 2025.05 Oral Paper Presentation (Top 8.5%) at Annual Research Showcase, MBZUAI, UAE
• 2025.04 Oral Paper Presentation at ISBI 2025 in the session “Vision-Language Model”, Houston, USA
• 2024.07 Ranked first among 177 applicants for the PhD position at University of Twente, Netherlands, 2024
• 2024.06 Secured Fully Funded Scholarship for Graduate School at MBZUAI for PhD program in Computer Vision
• 2023.11 Selected for Abstract Presentation, at PlanetX challenge by UAE Space Agency, Dubai Air Show, UAE
• 2023.09 Selected for Spotlight Presentation, at DART Workshop, 26th MICCAI, Vancouver, Canada
• 2023.07 Nominated for Best Paper Award, under Abstract Category, at 27th Conference on MIUA, Scotland
• 2022.08 Secured Fully Funded Scholarship for Graduate School at MBZUAI for MS program in Machine Learning
• 2018.12 Received Merit-Cum Means Scholarship, 2018 for attending bachelor’s program by Indian government

📖 Educations

• ^🎓 2024.08 - Present, PhD in Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.
• ^🎓 2022.08 - 2024, Masters in Machine Learning, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.
• ^🎓 2019.08 - 2022.06, Bachelors in Computer Science, Aligarh Muslim University, Aligarh, India.

💬 Services

• Journal Reviewer:
  • Nature Scientific Reports
  • IEEE Transactions on Circuits and Systems for Video Technology
  • ACM Transactions on Intelligent Systems and Technology
  • Springer Journal of Supercomputing
  • IEEE Access
  • Cryptologia
  • IEEE Transctions of Artificial Intelligence
• Conference Reviewer:
  • International Conference on Computer Vision (ICCV)
  • Winter Conference on Applications of Computer Vision (WACV)
  • Medical Image Understanding and Analysis (MIUA)
  • Sustainability and Resilience Conference (SRC)

💻 Experiences

• 2024.08 - Present, BioMedia Lab, Graduate Researcher, UAE.
• 2022.09 - 2024.07, Sprint-AI Lab, Graduate Researcher, UAE.
• 2023.06 - 2023.09, Fujairah Research Center, Visiting Researcher, UAE.
• 2021.03 - 2022.07, Aligarh Muslim University, Research Assistant, India.
• 2021.09 - 2021.12, National University of Malaysia, UKM, Research Intern, Malaysia.
• 2021.06 - 2021.08, Computer Science Society, AMU, Research Intern, India.
• 2021.05 - 2021.08, Indian Institute of Information Technology, Allahabad, Research Intern, India.

🎙 Miscellaneous

Travel

I enjoy traveling with my family and friends. I am always excited about visiting new places and learning about different cultures.

Sports

I love playing sports and always make time for football, badminton, and table tennis. I have played taekwondo professionally before and represented my university in badminton and table tennis competitions.

Football Team

MBZUAI Sports Week

Georgia Trip

Bouldering Clymb

Scotland Trip

Uzbekistan Trip