CV

B.S. in Computer Science

Carnegie Mellon University, Pittsburgh, PA

SCS Concentration in Machine Learning

AI Intern - NLP

MikoAI

Streamlined the multilingual personality module of the Miko robot, enhancing its language processing capabilities across 8 languages.

• Benchmarked open-source machine translation models towards optimizing cost-efficiency without compromising performance.
• Developed a neural classifier for question answering, achieving linear speedup over traditional vector search.

Dean's List with High Honors

CMU School of Computer Science

Fall 2021, Fall 2022, Spring 2023, Fall 2024

Where is this coming from? Making groundedness count in the evaluation of Document VQA models

NAACL 2025 Findings

Document VQA models have evolved at an impressive rate over the past few years. We propose a new evaluation methodology that accounts for the groundedness of predictions with regards to the semantic category of the output as well as the multimodal placement of the output within the input document. Through extensive analyses, we demonstrate that our proposed method produces scores that are a better indicator of a model's robustness, and tends to give higher rewards to better-calibrated answers.

AliGATr: Graph-based layout generation for form understanding

EMNLP 2024 Findings

Forms constitute a large portion of layout-rich documents that convey information through key-value pairs. In this paper, we present AliGATr, a graph-based model that uses a generative objective to represent complex grid-like layouts that are often found in forms. Using a grid-based graph topology, our model learns to generate the layout of each page token by token in a data efficient manner, performing at par with state-of-the-art models.