Muhammad Huzaifa

prof_pic.jpg

Masdar City, Abu Dhabi

Welcome to my Website! I am a PhD Researcher associated with the University of Tubingen working under Prof. Hilde. My research focuses on Efficient Multimodal Models. Previously, I also explored the robustness of vision models, and adaptation of vision-language models in scenarios with limited data, including few-/zero-shot setups.

I have also worked with Dr. Yova as a Research Associate.

I completed my Masters in Machine Learning from MBZUAI under the supervision of Dr. Salman Khan, Dr. Fahad Khan and mentored closely by Dr. Muzammal Naseer

Email / Google Scholar / Github / Twitter / CV

News

Feb 15, 2025 I have joined University of Tuebingen as a PhD Researcher working under the supervision of Prof. Hilde Kuehne
Feb 07, 2025 Served as a reviewer at CVPR’25
Jan 05, 2025 We have released EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval
Oct 29, 2024 Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization Accepted at WACV, 2025
Sep 15, 2024 ObjectCompose Accepted at ACCV for oral presentation!

View all news

Selected publications

* denotes joint first authors

  1. EFSA.png
    EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval
    Muhammad Huzaifa ,  and  Yova Kementchedjhieva
    2024
  2. ObjectCompose.jpg
    ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes
    Hashmat Shadab Malik* ,  Muhammad Huzaifa* ,  Muzzamal Naseer , and 2 more authors
    ACCV, 2024
  3. tta-raza.png
    Test-Time Low-Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
    Raza Imam ,  Hanan Gani ,  Muhammad Huzaifa , and 1 more author
    WACV, 2025
  4. defensive_diffusion.png
    On enhancing the robustness of vision transformers in medical imaging: Defensive diffusion
    Raza Imam* ,  Muhammad Huzaifa* ,  and  Mohammed El Amine Azz
    In 27th Conference on Medical Image Understanding and Analysis 2023 , 2023