I am an Applied Research Scientist at Adobe's Applied Research team working on language-vision research and Generative AI. I completed my PhD from the CS department at the Intelligent Visual Interfaces lab in Rutgers University . My PhD thesis was on Multimodal Story Comprehension, under the supervision of Dr. Mubbasir Kapadia and Dr. Gerard De Melo. My research interests are on joint understanding of images/videos and abstract/narrative text with applications to multimodal story comprehension. Specificaly, story illustration, visual storytelling, image captioning and text-to-image retreival/generation. Recently, I have been working on Diffusion Models for Image generation and editing. Some recent works are mentioned here.

News

• Mar 20, 2023: Our paper on PRedItOR: Inference time text guided image editing with Diffusion Prior is out on arXiv
• Feb 10, 2023: Our paper on Enhancing Controllability in Diffusion Models with a new Generalized Composable formulation is out on arXiv
• Jun 20, 2022: Our AESOP Dataset from ICCV 2021 is public at https://github.com/adobe-research/aesop
• Dec 1, 2021: Our paper on "Cross Modal Coherence for Text-to-Image Retrieval" is accepted at AAAI 2022.
• Sep 7, 2021: I am joining Adobe's Sensei ML team as an Applied Research Scientist.
• Aug 12, 2021: I have succesfully defended my PhD on Multimodal Story Comrpehension: Datasets, Tasks and Neural Methods.
• July 22, 2021: Our paper "AESOP: Abstract Encoding of Stories, Objects and Pictures" is accepted to ICCV 2021 main conference. Paper, Dataset and Code to follow soon.
• ...
• ...