Tajamul Ashraf

Tajamul Ashraf profile photo

CV | GitHub | LinkedIn
Google Scholar | Blog

I am currently a Research Manager at Nanyang Technological University, Singapore, working under the supervision of Prof. Adams Wai-Kin Kong. My current research is part of a joint initiative with INTERPOL Singapore, with a focus on video and temporal understanding. I received my Master's degree in Information Technology from the Indian Institute of Technology Delhi during which I had the privilege to intern at Microsoft Research. My Master's thesis was awarded the and my Bachelor's degree in Information Technology from the National Institute of Technology, Srinagar.

Outside research, I enjoy badminton and swimming. I am also passionate about creating positive social impact, which led me to initiate Ralith Milith, an anti-drug society in Kashmir. When I am not training models, I am usually training my badminton reflexes.

"What is now proved was once only imagined." -William Blake.

News

  • Mar 2026 : Our recent work CarePilot has been accepted to CVPR 2026 (Findings Track).
  • Mar 2026 : Grateful to receive the DEI ICLR 2026 registration and travel grant support.
  • Jan 2026 : Our paper Agent-X was accepted to ICLR 2026. Congratulations to all the authors!
  • Oct 2025 : Received the Outstanding Reviewer Award at MICCAI 2025.
  • Aug 2025 : Our team won Second Place in the AgentX Competition at the Agentic AI Summit 2025, UC Berkeley.
  • June 2025 : Thrilled to share that our paper TITAN has been accepted to the prestigious ICCV 2025!
  • June 2025 : Excited that our paper ToolSeg is accepted to MICCAI 2025!
  • Feb 2025 : Honored to serve as a reviewer for: ACM MM 2025, MICCAI 2025, WACV 2025, and ICCV 2025.
  • Dec 2024 : Humbled to be nominated as a Diversity Intern by Microsoft Canada! [Watch the announcement]
  • Oct 2024 : Grateful to receive the RISE-MICCAI travel grant to attend MICCAI 2024 in person!
  • Oct 2024 : Our work HF-Fed was accepted as an oral presentation at MICCAI-W 2024. Best Student Paper Award!
  • June 2024 : Successfully defended my Master’s synopsis at IIT Delhi
  • May 2024 : Proud to announce that D-MASTER has been accepted to MICCAI 2024!
  • Nov 2023 : Our paper got accepted at WACV 2024 – looking forward to sharing it with the community!
  • July 2023 : Presented our work at CVIP 2023. Grateful for the opportunity!
  • Mar 2023 : Our research was accepted at ICDSA 2023!
  • Jan 2023 : Contributed as a reviewer for CVIP 2022/23 and HPEC 2023.
  • Aug 2022 : Began my Master’s journey at IIT Delhi. An exciting chapter begins!
  • June 2022 : Graduated from NIT Srinagar with the prestigious Gold MSLA Award!
  • Feb 2021 : Won India’s largest National Entrepreneurship Challenge hosted by IIT Bombay. A game-changing experience!

Research

My research focuses on agents, with an emphasis on reasoning, grounding, and decision-making. I study how large multimodal models generalize across discriminative, generative, and perceptual tasks, particularly under out-of-distribution and federated settings. My work explores domain adaptation, reinforcement learning, and data-efficient learning to improve robustness and scalability. I am especially interested in building reliable agents for real-world applications in healthcare and embodied AI.

Publications

  • Representative
  • All
* indicates equal contribution, † indicates my role as mentor

Timeline

Community

    In my academic journey, I transitioned into a research-focused lifestyle, driven by a deep curiosity to explore Computer Vision and Medical Imaging. My path has been dynamic, with a domain shift from IoT to robotics, reflecting a continuous pursuit of learning and innovation. I am an advocate for open-source contributions, as they foster collective growth and help both educators and learners critically engage with the wealth of information available online. The guidance and support of my academic mentors and peers have been pivotal in shaping my early career, and their influence continues to inspire me.
    Building on this foundation, I am actively mentoring undergraduate and master’s students in computer vision, and I look forward to supporting more learners in the future. I particularly encourage students with diverse backgrounds or unconventional academic paths, similar to my own, to connect and explore opportunities for growth and research.
    If you are interested, send an introductory email that includes:
    - A brief introduction about yourself.
    - Your academic background and areas of interest.
    - Your CV (optional but preferred).