About / Research profile

Researching AI systems that reason, adapt, and generalize.

I work across multimodal reasoning, video understanding, large multimodal models, and self-evolving AI—with a focus on research that can move from controlled benchmarks into useful real-world systems.

Curriculum vitae ↗ Email

Biography

I am a PhD researcher at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).

My research spans multimodal reasoning, composed video retrieval, open-world video instance segmentation, large multimodal models, and self-evolving agentic systems. I am fortunate to be advised by Prof. Fahad Khan, Dr. Rao Anwer, and Dr. Salman Khan.

I am particularly interested in connecting foundational research with real-world deployment. My work includes efficient language models, on-device multimodal retrieval, and applied AI platforms. During my PhD, I am also working as a Research Scientist Intern at Adobe Research from June to September 2026.

Research Scientist Intern · Jun 2026–Sep 2026: Adobe Research
PhD Researcher · Aug 2023–present: Mohamed bin Zayed University of Artificial Intelligence, UAE
Researcher · Nov 2021–Jul 2023: Mohamed bin Zayed University of Artificial Intelligence, UAE
Machine Learning Engineer · Feb 2020–May 2021: Chefling India Pvt. Ltd.
Research Assistant · Jan 2019–Feb 2021: Indian Institute of Technology Ropar, India

Research interests

My research connects multimodal understanding with efficient, adaptive, and deployable intelligence.

Multimodal Learning and Reasoning

Grounded reasoning across images, video, language, and structured information using large multimodal models.
Primary
Video Understanding and Retrieval

Composed retrieval, temporal understanding, dense video modifications, and explainable media search.
Primary
Agentic and Self-Evolving AI

Systems that improve through continuous feedback, tool use, retrieval, and interaction with real environments.
Primary
Open-World Learning

Visual systems that identify unknown concepts and generalize beyond fixed vocabularies and closed-world assumptions.
Primary
Efficient and Transparent Models

Compact LLMs and LMMs designed for reproducibility, interpretability, and resource-constrained deployment.
Secondary
Multilingual and Cultural AI

Evaluation and adaptation of multimodal systems across languages, cultures, and specialist domains.
Secondary
Retrieval and Long-Horizon Reasoning

Retrieval-augmented generation, world models, and structured reasoning over extended contexts.
Secondary