About Me

I am a PhD student (submitted thesis) in the Computer Science Department at Ashoka University. My advisor is Dr. Debayan Gupta and co-advisor is Dr. Indra Deep Mastan. I am working with Vision-Language models for controllable image transformations, specifically on making image edits semantic-aware, so that object identity and spatial structure remain intact under style or text-guided changes.

I am also interested in learning rich representations learned within the latent spaces of large-scale generative models and leveraging them for downstream tasks. My long-term research goal is to bridge the gap between possibility and practicality.

I began my research career at IITGn under the guidance of Dr. Dinesh Garg, who broadened my interests in Deep Generative Models and Natural Language Processing. I then embarked on my PhD journey at Ashoka University, mentored by the remarkable (the late) Dr. Ravi Kothari.

Dr. Ravi brought me into the PhD program and fostered my research interests in multimodal learning, particularly in the vision and language domains. I am deeply grateful for his wisdom, guidance, support, encouragement, and the lasting impact he has had on my life and career.

Research Interests:

Robust Representations, Multimodal Learning, Generative Models, Transfer Learning.

Work Experience:

. Data Analyst at Tata Consultancy Services, Delhi [Sept, 2014 - July, 2017] . Research Fellow at Mphasis (Nov, 2020 - Dec 2023)

Education:

. PGDIIT at Indian Institute of Technology Gandhinagar (July 2017 - Dec 2018).
. M.Tech in Computer Science from Banasthali Vidyapith (Research Intern at C-DAC, Noida) [2012-2014].
. B.Tech in Computer Science from Maharishi Dayanand University[2008-2012].