Monjoy Narayan Choudhury — accepted AI-conference papers

2025

Can Vision-Language Models Solve Visual Math Equations?

Monjoy Narayan Choudhury, Junling Wang, Yifan Hou, Mrinmaya Sachan

EMNLP 2025

Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images,

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

CASE: Efficient Curricular Data Pre-training for Building Assistive Psychology Expert Models

Sarthak Harne, Monjoy Narayan Choudhury, Madhav Rao, T K Srikanth, Seema Mehrotra, Apoorva Vashisht +2

EMNLP 2024finding

The limited availability of psychologists necessitates efficient identification of individuals requiring urgent mental healthcare. This study explores the use of Natural Language Processing (NLP) pipelines to analyze text data from online mental health forums used for consultations. By analyzing for…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗