Devan Shah

I am a third year undergraduate in Computer Science at Princeton University pursuing a minor in mathematics. I am currently a member of the Hazan Lab led by Prof. Elad Hazan.

Broadly, I am interested in post-transformer architectures, such as state space models, and applications of machine learning to understanding thought and behavioral patterns. I currently work on understanding relaxations of state space models (i.e. the spectral transform unit). At Princeton, I cohost a reading group in natural language processing and chair our ACM chapter, with a general hope of increasing accessibility to research.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Download Profile Picture (Square)

Work Experience
project image

Recommendation Systems at TikTok

May 2024 — August 2024

I improved the recommendation system for ecommerce videos for a projected $33,000,000+ increase in annual sales . I primarily focused on improving multi-interest modeling, training novel generative models (10B+ parameters) to better parameterize the interest space.
project image

EEG Vision Embeddings at CareYaya

November 2023 — May 2024

As a research scientist at CareYaya Health Technologies, I studied the reconstruction of viewed images from brain activity, improving performance by conditioning on additional user information. We aimed to better align EEG embeddings with CLIP space.
project image

Scooter Authentication at Cal Poly Pomona

June 2023 - April 2024

At Cal Poly Pomona, I worked on continuously authenticating mobility scooter riders based on their posture patterns. We worked on embedding machine learning techniques for light-weight authentication and studied human motion in the search for a biometric identifier.
project image

Price Prediction at Ticket Wallet

June 2023 — August 2023

At Ticket Wallet, I worked closely with the CEO in an early-stage startup to advise and design data pipelines, pricing algorithms, and refine product pitches. Engineered the backend authentication and created a multi-modal ticket prediction system.



Research
project image

ScooterId: Posture-Based Continuous User Identification From Mobility Scooter Rides


Devan Shah , Ruoqi Huang, Nisha Vinayaga-Sureshkanth, Tingting Chen, Murtuza Jadliwala
IEEE TMC 2024
paper

project image

Rider Posture-Based Continuous Authentication with Few-Shot Learning for Mobility Scooters (Student Abstract)


Devan Shah , Ruoqi Huang, Tingting Chen, Murtuza Jadliwala
AAAI 2023
paper




Projects

project image

Truly Adaptive Bloom Filters


Devan Shah* , David Yan* (Equal Contribution)
COS 598
paper

project image

Understanding Dynamic Algorithms for Packing-Covering LPs via Multiplicative Weight Updates


Devan Shah* , Owen Yang*, Sunil Vittal* (Equal Contribution)
COS 521
paper

project image

DreamScape: Denoising CLIP Embeddings with User Images for Improved Visualization Reconstruction


Devan Shah
CareYaya
paper




Coursework

Computer Science
COS217 Introduction to Programming Systems (C and Assembly)
COS226 Algorithms and Data Structures
COS418 Distributed Systems
ECE435* Machine Learning and Pattern Recognition
COS597 Long Term Memory in AI - Vector Search and Databases
COS597 Systems and Machine Learning

Theory
ECE434 Theoretical Machine Learning
COS521 Advanced Algorithm Design
COS522 Computational Complexity
COS585 Information Theory and Applications
ORF543* Deep Learning Theory
COS598* Theory of Natural Algorithms

Math
MAT216 Multivariable Analysis and Linear Algebra I
MAT218 Multivariable Analysis and Linear Algebra II
ECO310 Microeconomic Theory: A Mathematical Approach
MAT377 Combinatorial Mathematics
MAT385* Probability Theory
MAT478 The Probabilistic Method

Creative Writing

FRS116 Evolution of Human Language
CWR202 Creative Writing (Poetry)
ATL494 Creating Comedy for Television
ATL497 How to Write a Monologue

* denotes ongoing course

Design and source code from David Yan's fork of Alexander Raistrick's fork of Leonid Keselman's Jekyll fork of Jon Barron's website