I am Sohan, a Research Associate at the Media and Data Science Research Lab at Adobe, where I contribute to the integration of advanced AI features into various products. I hold a dual degree in Mechanical Engineering from the Indian Institute of Technology (IIT), Kharagpur.

My primary research interests lie in vision-language models and the development of agentic frameworks & autonomous agents for several workflow automation tasks. I focus on designing autonomous agents capable of addressing complex, real-world challenges by leveraging multimodal data and implementing efficient interaction mechanisms.

I have authored several publications in leading conferences and journals, including ICLR, EMNLP, AAAI, NAACL, and TMLR. My research approach is deeply rooted in identifying and solving problems that align with practical product applications, bridging the gap between theoretical advancements and real-world impact.