Sree Bhattacharyya

About Me

I am a second-year PhD student at Pennsylvania State University, in the College of Information Sciences and Technology, where I am advised by Dr. James Z. Wang. My broad area of research interest is multimodal AI, with a focus on improving abtract, subjective reasoning capabilities in multimodal AI models - such as emotional, cultural, or social understanding. At present, I am working on the following (and/or asking the following research questions):

• Can we model and automatically predict what emotions are expressed through body language/gestures?
• Using theories from cognitive science and neuroscience to better inform model design for emotion understanding.
• What are some general improvements in VLMs that can enhance their capabilities in a wide range of subjective reasoning tasks (eg., personality alignment, etc.)?
• How can we predict the memorability of some content? (In collaboration with Dr. Yaman K. Singla, and Somesh Singh from Adobe MDSR Labs, India)

Prior to joining my PhD, I was a Software Engineer at Microsoft, India, working with Azure storage. I graduated with a B.Tech. in Computer Science from IIEST Shibpur in 2022.

As an undergraduate student, I was fortunate to have been advised by Prof. Chris Biemann at the University of Hamburg, for my internship as a DAAD WISE Scholar. I worked on improving lexical resources for low-resource languages during this internship, where I also closely worked with Dr. Abhik Jana. For my undergraduate thesis at IIEST, I worked on applications of graph learning, and explored areas like medical diagnosis using GNNs, and social network analysis.

Besides academics, I love music in any and every form. I trained in Indian classical and folk music vocals for almost 2 decades, often performing professionally in India. I also enjoy theatre, and was part of a professional group for over 6 years. These days, I am learning how to play the piano, and trying to understand Western classical music (with the distant dream of performing in a musical someday!). I enjoy trying to play tennis (which I am extremely bad at!), and swimming.

News

• [Jan. 2025] “Evaluating Vision-Language Models for Emotion Recognition” accepted to NAACL ‘25 Findings!
• [June 2024] My first PhD project got accepted as a paper at ACII 2024 for oral presentation!
• [Aug. 2023] I started my PhD at Penn State!
• [July 2023] I completed a year at Microsoft!
• [June 2023] My undergrad thesis got accepted as a workshop paper at IJCAI!

Publications

Powered by Jekyll and Minimal Light theme.