Yash Shah

I am a Master's student in Computer Science, part of the School of Engineering at Stanford University. I matriculated in 2023 and am specializing in Artificial Intelligence.

Previously, I received my Bachelor's degree (Summa Cum Laude) from University of California, San Diego between 2019 and 2023, where I majored in Computer Science and minored in Humanities. There, I worked in Dr. Nadir Weibel's and Dr. Garrison Cottrell's labs and was a course assistant for CSE 151B under Dr. Garrison Cottrell (Fall 2022) and Dr. Rose Yu (Spring 2023).

Email  /  GitHub  /  LinkedIn  /  Paintings  /  Quotes

profile photo

Research

I'm broadly interested in biologically-plausible AI for vision and language, applications of AI in healthcare, and generative AI.

project image

Convolutional Neural Networks With Divisive Normalization Across Similar Features


Yash Shah, Xuzhe Zhi, Keyu Long, Garrison Cottrell
2023-06

In this paper, we explore using divisive normalization across neuronal sub-populations computing similar features, with and without an associated rectifier like ReLU, to enforce local competition. We create these neuronal sub-populations that compute similar features by sampling the weights for NxN convolutional filters from a multivariate N^2–dimensional gaussian distribution. Results are analyzed based on top-1 accuracy and computation speed on CIFAR-10 and CIFAR-100.

project image

iContour: Design and Development of a Cross–Platform Contouring System in Healthcare Treatment and Education


Matin Yarmand, Chen Chen, Michael Sherer, Yash Shah, Peter Liu, Larry Hernandez, James D. Murphy, Nadir Weibel
2022-06

This paper presents iContour: the first cross-platform interface that enables examining and contouring medical images, a critical step in radiotherapy treatment planning aimed at identifying and segmenting tumors, not only on desktop computers, but also on everyday touch devices.




Industry Experience

A collection of my internship and full-time projects.

project image

Software Engineer


PayPal | Team Network Tokenization
2023-07 to 2023-09

Queried ~8M cards for various merchants using PostgreSQL and submitted for bulk network token enrollment. Analyzed 3-D secure transactions for 118 merchants and (1) enabled them to be processed through network tokenization first in production, (2) modified the way 3-D secure transactions are processed for certain processors and card types in the codebase so that future transactions can be directly processed through NT First.

project image

Software Engineer Intern


PayPal | Team Network Tokenization
2022-06 to 2022-09
poster /

Enabled network tokenization first for payment transaction processing for PayPal’s merchant partners to improve security and optimize authorization rates by around 40% for some merchants. Utilized data monitoring tools for monitoring code changes. Added a Foreign Tax ID Prompt to the Token Requestor ID (TRID) Onboarding UI to enable foreign merchants to apply for network tokenization.

project image

Technology Development Intern


Optum | Team OptumRx
2021-06 to 2021-08

Developed a client portal using React and TypeScript and made Axios calls to the server using React Redux to onboard clients and allow them to place requests for Optum’s API services. Performed interface and architecture design research before building the portal for seamless user experience. Influenced company executives by presenting the business benefits of my project at Shark Tank presentations.




Other Technical Projects

These include coursework and side projects.

project image

You Text, We Sketch: Text-guided Diffusion For Vectorized Sketch Generation


Yash Shah*, Samy Cherfaoui* (*equal contribution)
Stanford University CS 236
2023-12
paper / poster /

In this paper, we explore text-conditioned diffusion models for vectorized sketch generation by conditioning on text during training by feeding text tokens into a Transformer used as a text encoder, and introduce classifier-free guidance to improve sample quality.

project image

Can a Set of Calibrated Weak Learners Create a Single Calibrated Strong Learner?


Yash Shah*, Minseok Bae*, Jason Park* (*equal contribution)
Stanford University CS 229
2023-12
paper / poster /

In this paper, we propose a unique way of implicitly calibrating AdaBoost (a traditional Machine Learning ensemble classifier) during training (as opposed to other post-hoc state-of-the-art techniques) through doubly-calibrating individual weak learners in the ensemble.

project image

Image Captioning with Recurrent Neural Networks


Henry Lister*, Ryan Nishimoto*, Yash Shah* (*equal contribution)
UC San Diego CSE 151B
2022-03
paper /

In this work we present and analyze the working of a deep RNN in action by captioning images taken from the Microsoft COCO 2014 dataset. We explore various learning rate schedulers, ways of embedding and encoding, LSTMs, temperatures, etc.

project image

PomoHero


Muhammad Z Khan*, Xavier Tan*, James Zhao*, Ivan Robles*, Yash Shah*, Haaris Waleh*, Mrinmoy Dutta* (*equal contribution)
UC San Diego CSE 110
2021-03
website /

A Pomodoro timer, based on the Pomodoro technique to help users better organize their schedules and get work done through time management.




Non-Technical Projects

From my Humanities minor.

project image

Gender and Sexuality Through the Visual Imagery of Colors


UC San Diego LTEU 141
2023-03
paper /

In the stories of Colette and in Les Guérillères by Monique Wittig, we see different colors appear in different stories, bringing with them different symbolic connotations that may highlight themes within these stories that are not evident at first. Trying to interpret the visual imagery that colors bring might help us answer questions concerning why Colette and Wittig use them in the first place.

project image

Thematization and Same-Sex Desire in “Song of the Ugly Maiden”


UC San Diego LTEN 127
2022-11
paper /

An interpretation of Eliza Cook’s poem “Song of the Ugly Maiden” is her yearning for a love for women. In this paper, I argue for this through analyzing thematization the occurs in the poem through rhyme scheme deviations, use of alliterations, word choices, and Cook having the Ugly Maiden sing her song as an interior monologue.

project image

Women and Power in The Merchant of Venice


UC San Diego LTEN 112
2022-06
paper /

One of the questions that Shakespeare raises in his play The Merchant of Venice is the ability of women to have autonomy and exercise power. This autonomy and power, however, is confined to the domestic sphere between the husband and the wife. In the public sphere, women get to exercise power when they disguise themselves as men. Shakespeare, by portraying women in this manner, challenges the conventional social system of patriarchy.

project image

The Plowman's Tale in The Canterbury Tales


UC San Diego LTEN 107
2021-11
paper /

An exercise in creative and imaginative writing, this paper presents a poem that the Plowman in Geoffrey Chaucer’s The Canterbury Tales could have sung if he were given a speaking role. A possible theme, which this paper presents, is the Plowman’s narration of the events of the Peasant’s Revolt of 1381 and an attempt to “quite” Chaucer.

project image

Du Bois, Racial Equality, and Gender Equality


UC San Diego HUM 5
2021-05
paper /

In this argumentative essay, I view W. E. B. Du Bois’ text The Souls of Black Folk, being an undertaking for racial equality for Black Americans, through the lens of Simone de Beauvoir and her text The Second Sex, which has become, arguably, a classic text for the advocation of gender equality for women.




Honors and Awards

Across the years...

project image

Computer Science and Engineering Department Excellence Award


by Jacobs School of Engineering Ring Ceremony, UC San Diego
2023-06

for outstanding academic and leadership performance, and exceptional contributions to university life.

project image

Christine Norris Award


by Revelle College, UC San Diego
2023-05

for outstanding achievement in The Humanities.

project image

Revelle College Provost’s Honors Certificate


by Revelle College, UC San Diego
2021-10

for achieving a minimum grade point average of 3.5 for at least 12 graded units for all three quarters in an academic year.

project image

Revelle College Provost’s Honors Certificate


by Revelle College, UC San Diego
2020-09

for achieving a minimum grade point average of 3.5 for at least 12 graded units for all three quarters in an academic year.

project image

Outstanding Leadership Award


by Revelle Hall Association, UC San Diego
2019-12

for exceptional efforts in guiding others and ensuring the success of “Pick-A-Pal” event.

project image

Exceptional Diligence Award


by Revelle Hall Association, UC San Diego
2019-12

for outstanding dedication to the programs executed in the 2019 Fall Quarter.


Design and source code from the Jekyll fork by Leonid Keselman of Jon Barron's website