Pink floral background with decorative pattern

Welcome!

Featured Projects

Something Brazen

My work on Brazen, a platform connecting women entrepreneurs with angel investors. I gained valuable experience in entrepreneurship and designing for startups, building wireframes on Figma and a low-code MVP on bubble.io

6.805 Final Project

For our final project in 6.805 (Foundations of Information Policy), I developed a pool-based active learning algorithm to generate personalized data privacy policies. I used Adobe XD to create example UIs prototyping our recommendations.

6.835 Final Project: Kalpana

We built a D&D-inspired multimodal spellcasting game focused on teaching users how to perform various spells using both speech and gesture recognition, and in turn, use these spells to attack and defeat a variety of enemies.

Papers + Reports

Master of Engineering Thesis

This research presents the development of homo-silicus, a Python-based library for simulating economic experiments and social scenarios using AI subjects. Using the library, users can design, test, and analyze results of experiments conducted in silico.

6.08 Introduction to EECS via Interconnected Embedded Systems

Our project focused on creating a group Spotify party hosting platform where each user is allowed to add songs to a shared song queue which will be played out of an IOT-connected speaker.

6.864 Advanced Natural Language Processing

In this paper, we applied a variety of model architectures to the problems of song lyric classification and generation.

6.804 Computational Cognitive Science

Speech alternatives enable listeners to draw pragmatic inferences in language understanding. We modeled how the proportion of people who inferred directness from a verb with no lexical causative form used in the periphrastic form was greater than from a verb with a lexical causative form.

6.805 Foundations of Information Policy

Here, we discussed the ensuing harm from users’ lack of control over smart home technologies, and best practices to minimize their privacy risks. We propose and compare three recommended policies and their limitations on both commercial producers and users