I am a PhD student and Powell Fellow in Computer Science at UC San Diego, advised by Prof. Manmohan Chandraker. I am also supported by Powell Fellowship and UCSD Jacobs School of Engineering Fellowship.

Before UCSD, I completed my Master's in Machine Learning at MBZUAI in the IVAL lab, advised by Prof. Salman Khan and co-advised by Prof. Fahad Khan, and mentored by Dr. Muzammal Naseer. I previously worked as a Research Associate II at MBZUAI. I also worked as a visiting student with Prof. Peter Wonka at KAUST.

Research Focus

Intelligent Agentic Systems

Building multimodal agents that plan, reason, and act robustly in open-ended tasks.

World and Mental Models

Learning predictive internal models for simulation, decision support, and long-horizon behavior.

Spatial Reasoning

Developing representations and inference mechanisms for geometry-aware visual understanding.

Embodied AI

Designing grounded intelligence for perception, control, and interaction in physical environments.

Career Trajectory

UC San Diego logo

University of California, San Diego

PhD in Computer Science
2025 to Present

MBZUAI logo

MBZUAI

Research Associate II
2024 to 2025

MBZUAI logo

MBZUAI

MS in Machine Learning
2022 to 2024

KAUST logo

KAUST

Visiting Student
2023

Samsung logo

Samsung

Machine Learning Engineer
2018 to 2021

NIT Srinagar logo

NIT Srinagar

Bachelor's in ECE, Minor in CS
2014 to 2018

Recent News

  • Mar 2026

    One paper accepted at ML4RS workshop at ICLR 2026.

  • Jan 2026

    Agent-X accepted at ICLR 2026.

  • Sep 2025

    Began my PhD in Computer Science at UC San Diego.

  • Sep 2025

    Placed 2nd in the research track at UC Berkeley's AgentX challenge.

  • Jun 2025

    Aurelia accepted at ICCV 2025.

  • Mar 2025

    VideoGLaMM accepted at CVPR 2025.

  • Jan 2025

    VANE-Bench accepted at NAACL 2025.

  • Mar 2024

    Awarded ICLR 2024 Travel Grant.

  • Oct 2023

    Awarded NeurIPS 2023 Travel Grant.

Selected Publications

  1. Under Review
    VideoMolmo: Spatio-Temporal Grounding meets Pointing
    Ghazi Shazan Ahmad*, Ahmed Heakl*, Hanan Gani, Abdelrahman Shaker, Zhiqiang Shen, Ranjay Krishna, Fahad Shahbaz Khan, Salman Khan
    Under Review
    PDF Project page Code

  2. ICLR 2026
    Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
    Tajamul Ashraf*, Amal Saqib*, Hanan Gani, Muhra AlMahri, Yuhao Li, Noor Ahsan, Umair Nawaz, Jean Lahoud, Hisham Cholakkal, Mubarak Shah, Philip Torr, Fahad Shahbaz Khan, Rao Muhammad Anwer, Salman Khan
    Internal Conference on Learning Representations (ICLR) 2026
    PDF Dataset Code

  3. ICCV 2025
    Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs
    Sanjoy Chowdhury*, Hanan Gani*, Nishit Anand, Sayan Nag, Ruohan Gao, Mohamed Elhoseiny, Salman Khan and Dinesh Manocha
    IEEE/CVF International Conference on Computer Vision (ICCV) 2025
    PDF Code

  4. CVPR 2025
    VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
    Shehan Munasinghe*, Hanan Gani*, Wenqi Zhu, Jiale Cao, Eric Xing, Fahad Khan and Salman Khan
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
    PDF Project page Code

  5. NAACL 2025
    VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
    Hanan Gani*, Rohit Bhardwaj*, Muzammal Naseer, Fahad Khan and Salman Khan
    Findings of the Association for Computational Linguistics (NAACL) 2025
    PDF Project page Code

  6. COLING 2025
    AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model Alignment
    Umair Nawaz, Muhammad Awais, Hanan Gani, Muzammal Naseer, Fahad Khan, Salman Khan, Rao Muhammad Anwer
    International Conference on Computational Linguistics (COLING) 2025
    PDF Code

  7. WACV
    Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
    Raza Imam, Hanan Gani, Muhammad Huzaifa and Karthik Nandakumar
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
    PDF Code Poster Presentation

  8. MICCAI
    MedContext: Learning Contextual Cues for Efficient Volumetric Medical Segmentation
    Hanan Gani, Muzammal Naseer, Fahad Khan and Salman Khan
    27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2024
    PDF Code Poster Presentation

  9. ICLR
    LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
    Hanan Gani, Shariq Farooq Bhat, Muzammal Naseer, Salman Khan, Peter Wonka
    12th International Conference on Learning Representations (ICLR) 2024
    PDF Code Project Page Poster Slides & Video Poster Presentation

  10. NeurIPS
    Align your Prompts: Test-time Prompting with Distribution Alignment for Zero-shot Generalization
    Jameel Hassan *, Hanan Gani *, Noor Hussein, Uzair Khattak, Muzammal Naseer, Fahad Khan, Salman Khan
    37th Advances in Neural Information Processing Systems (NeurIPS), 2023
    PDF Code Project Page Poster Slides & Video Poster Presentation

  11. BMVC
    How to Train Vision Transformer on Small-scale Datasets?
    Hanan Gani, Muzammal Naseer, Mohammad Yaqub
    33rd British Machine Vision Conference 2022, (BMVC), London, UK.
    PDF Code Project Page Poster Video slides Poster Presentation

  12. IEEE ICIP
    Multi-Attribute Vision Transformers are Efficient and Robust Learners
    Hanan Gani, Nada Saadi, Noor Hussein and Karthik Nandakumar
    IEEE ICIP 2024
    PDF Code Poster Presentation

  13. Arxiv
    A Supervised Learning Methodology for Real-Time Disguised Face Recognition in the Wild
    Saumya Kumaar, Abhinandan Dogra, Abrar Majeedi, Hanan Gani, Ravi M. Vishwanath and S N Omkar
    ACM International Conference on Robotics and Computer Vision (ICRCV), 2018
    PDF Code Arxiv Paper

  14. ICSIP
    Disguised Facial Recognition Using Neural Networks
    S Kumaar, H. Gani, RM Vishwanath, SN Omkar, A Majeedi, A Dogra
    IEEE 3rd International Conference on Signal and Image Processing (ICSIP), 2018
    PDF Code Poster Presentation

Patents

  1. US-Patent
    System and method of training vision transformer on small-scale datasets
    Hanan Gani, Muzammal Naseer and Mohammad Yaqub
    US Patent, 2024
    PDF

Academic Service

Conference Reviewing

  • Regular reviewer at ICLR, AAAI, NeurIPS, ECCV, CVPR, ICML, ICCV.

Teaching Assistant

Conference Volunteering

  • Program volunteer at IEEE ICIP (Abu Dhabi).

Invited Talks

  • May 2025: Delivered a talk on "Latest Trends in AI" at Abu Dhabi University.
  • June 2024: Presented a talk on "Generative AI" for undergraduate CS students at the University of Jordan.

Awards and Honors

Powered by Jekyll and Minimal Light.