Publications

2026

1. 

   Any-to-Any Video Modeling in Multimodal Abstract Spaces

   Muhammad Uzair Khattak, Won Jun Kim, Reza Abbassi, Michael Murphy, Amir Zadeh, Chuan Li, Oguzhan Fatih Kar, Muhammad Ferjad Naeem, Andrei Atanov, Roman Bachmann, Federico Tombari, and Amir Zamir

   Under Review, 2026

2024

1. 

   UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities

   Muhammad Uzair Khattak*, Shahina Kunhimon*, Muzammal Naseer, Salman Khan, and Fahad Shahbaz Khan

   arXiv preprint arXiv:2412.10372, 2024

   Bib PDF Code

   @article{khattak2024unimed,
     author = {Khattak*, Muhammad Uzair and Kunhimon*, Shahina and Naseer, Muzammal and Khan, Salman and Khan, Fahad Shahbaz},
     title = {UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities},
     journal = {arXiv preprint arXiv:2412.10372},
     year = {2024},
   }

2. 

   How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs

   Muhammad Uzair Khattak, Muhammad Ferjad Naeem, Jameel Hassan, Muzammal Naseer, Federico Tombari, Fahad Shahbaz Khan, and Salman Khan

   arXiv preprint arXiv:2405.03690, 2024

   Bib PDF Code Website

   @article{khattak2024complex,
     author = {Khattak, Muhammad Uzair and Naeem, Muhammad Ferjad and Hassan, Jameel and Naseer, Muzammal and Tombari, Federico and Khan, Fahad Shahbaz and Khan, Salman},
     title = {How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs},
     journal = {arXiv preprint arXiv:2405.03690},
     year = {2024},
   }

3. 

   Learning to Prompt with Text Only Supervision for Vision-Language Models

   Muhammad Uzair khattak, Muhammad Ferjad Naeem, Naseer Muzzamal, Luc Van Gool, and Federico Tombari

   arXiv:2401.02418, 2024

   Bib PDF Code Website

   @article{Khattak2024ProText,
     title = {Learning to Prompt with Text Only Supervision for Vision-Language Models},
     author = {khattak, Muhammad Uzair and Naeem, Muhammad Ferjad and Muzzamal, Naseer and Gool, Luc Van and Tombari, Federico},
     journal = {arXiv:2401.02418},
     year = {2024},
   }

2023

1. 

   Maple: Multi-modal prompt learning

   Muhammad Uzair Khattak, Hanoona Rasheed, Muhammad Maaz, Salman Khan, and Fahad Shahbaz Khan

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

   Bib PDF Code Website

   @inproceedings{khattak2023maple,
     title = {Maple: Multi-modal prompt learning},
     author = {Khattak, Muhammad Uzair and Rasheed, Hanoona and Maaz, Muhammad and Khan, Salman and Khan, Fahad Shahbaz},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {19113--19122},
     year = {2023},
   }

2. 

   Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization

   Jameel Hassan, Hanan Gani, Noor Hussein, Muhammad Uzair Khattak+, Muzammal Naseer, Fahad Shahbaz Khan, and Salman Khan

   Advances in Neural Information Processing Systems, 2023

   Bib PDF Code Website

   @article{hassan2023align,
     title = {Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization},
     author = {Hassan, Jameel and Gani, Hanan and Hussein, Noor and Khattak+, Muhammad Uzair and Naseer, Muzammal and Khan, Fahad Shahbaz and Khan, Salman},
     journal = {Advances in Neural Information Processing Systems},
     year = {2023},
   }

3. 

   Fine-tuned clip models are efficient video learners

   Hanoona Rasheed*, Muhammad Uzair Khattak*, Muhammad Maaz, Salman Khan, and Fahad Shahbaz Khan

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

   Bib PDF Code Website

   @inproceedings{rasheed2023fine,
     title = {Fine-tuned clip models are efficient video learners},
     author = {Rasheed*, Hanoona and Khattak*, Muhammad Uzair and Maaz, Muhammad and Khan, Salman and Khan, Fahad Shahbaz},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {6545--6554},
     year = {2023},
   }

4. 

   Self-regulating Prompts: Foundational Model Adaptation without Forgetting

   Muhammad Uzair Khattak*, Syed Talal Wasim*, Muzammal Naseer, Salman Khan, Ming-Hsuan Yang, and Fahad Shahbaz Khan

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Oct 2023

   Bib PDF Code Website

   @inproceedings{Khattak_2023_ICCV,
     title = {Self-regulating Prompts: Foundational Model Adaptation without Forgetting},
     author = {Khattak*, Muhammad Uzair and Wasim*, Syed Talal and Naseer, Muzammal and Khan, Salman and Yang, Ming-Hsuan and Khan, Fahad Shahbaz},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {15190-15200},
     year = {2023},
     month = oct,
   }

5. 

   Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition

   Syed Talal Wasim*, Muhammad Uzair Khattak*, Muzammal Naseer, Salman Khan, Mubarak Shah, and Fahad Shahbaz Khan

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023

   Bib PDF Code Website

   @inproceedings{Wasim_2023_ICCV,
     author = {Wasim*, Syed Talal and Khattak*, Muhammad Uzair and Naseer, Muzammal and Khan, Salman and Shah, Mubarak and Khan, Fahad Shahbaz},
     title = {Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
     month = oct,
     year = {2023},
     pages = {13778-13789},
   }

2022

1. 

   Bridging the gap between object and image-level representations for open-vocabulary detection

   Hanoona Bangalath*, Muhammad Maaz*, Muhammad Uzair Khattak, Salman H Khan, and Fahad Shahbaz Khan

   Advances in Neural Information Processing Systems, Oct 2022

   Bib PDF Code Website

   @article{bangalath2022bridging,
     title = {Bridging the gap between object and image-level representations for open-vocabulary detection},
     author = {Bangalath*, Hanoona and Maaz*, Muhammad and Khattak, Muhammad Uzair and Khan, Salman H and Shahbaz Khan, Fahad},
     journal = {Advances in Neural Information Processing Systems},
     volume = {35},
     pages = {33781--33794},
     year = {2022},
   }

2. 

   Investigating and Improving Common Loop Closure Failures in Visual SLAM

   Saran Khaliq, Muhammad Latif Anjum, Wajahat Hussain, Muhammad Uzair Khattak, and Momen Rasool

   Autonomous Robots, Oct 2022

   PDF