Research Philosophy

My research philosophy is centered on the generative capabilities of vision–language models, large language models, and diffusion models. These systems extend beyond traditional discriminative modeling by enabling richer representation learning, knowledge transfer, and multimodal synthesis. I am interested in how such generative approaches can expand the scope of reasoning and adaptability in modern AI.

Equally important to me is the pursuit of fairness and robustness in these systems. Generative models offer unique opportunities to uncover and mitigate hidden biases, improving generalization across diverse settings. By combining advances in generative modeling with principles of fairness, I aim to contribute to the development of AI that is both innovative in capability and responsible in deployment.

Current Focus

At Imperial College London, I'm exploring:

• Exploring Diffusion Models for Personalization Exploring LoRA-based personalization to capture a subject’s signature micro-expressions and phrase-specific articulation patterns, and transfer these traits to target identities and languages while preserving lip-sync fidelity.
• Bias mitigation with generative methods: Exploring the use of generative frameworks to promote fairness in classifiers.

Beyond Research

I like to play Clash Royale, Chess, and FIFA in my free time.

Get in Touch

I'm always interested in research collaborations, discussing new ideas, or opportunities to contribute to impactful AI research. Feel free to reach out!