Shreyosi Endow

I’m a PhD candidate in Computer Engineering at the University of Texas at Arlington, specializing in Human-Computer Interaction under the advisement of Dr. Cesar Torres. My research interests span natural language processing (NLP), crowdsourcing, large language models (LLMs), and design research. I develop automated and scalable techniques for extracting tacit knowledge from instructional content available on the web to better support tutorial search, generation, and navigation. My broader goal is to reshape how we think about knowledge transfer by moving beyond one-size-fits-all instruction towards richer, experiential, and more pluralistic forms of learning that honor intuition, care, and variation.

Throughout my PhD, I have been very fortunate to participate in a set of research internships. At Adobe Research, I leveraged my background in wearables and sensing to contribute to Project Primrose where I integrated motion-responsive behavior into a dynamic computational dress display. I worked at the intersection of HCI and computer vision during an internship at Fujitsu Research, where I built a VLM-powered interactive system for evaluating the quality of large image datasets used for 3D reconstruction workflows. Currently, I am interning at Adobe Research with Christine Dierk and Eunyee Koh at Adobe Research, where I am exploring how generative AI can enable new creative workflows and augment the design process itself.