Parth with llama

Parth training llamas :)

Google Scholar
GitHub
Twitter
LinkedIn

Parth Sarthi

Hello! I am a third year BS/MS student in Computer Science at Stanford University, working on deep generative models with applications in language modeling, controllable speech synthesis and more.

I am an undergraduate researcher in the Stanford NLP Group and Stanford AI Lab, working under Professor Chris Manning. My research has contributed to state-of-the-art retrieval augmented systems. I was a part of Stanford NLP’s Chirpy Cardinal team, in the Amazon Alexa Socialbot Grand Challenge 5, where we secured the first place and a $250K prize in the Science category. There, I was responsible for the Pre-Firing Project, which aimed to predict user responses to improve response time. I was a Member of Technical Staff at Contextual AI, where I worked on training retrieval augmented language models.

Please reach me at psarthi at stanford.edu

News: RAPTOR got accepted at ICLR 2024.


Honors

My team and I won the Best Project (Sponser’s Prize) in CS224N (out of 650+ students).

My team and I were finalists at MIT Bitcoin Expo 2022 - Breaking Through Hackathon for creating a decentralized database validation protocol: ValGun.

My team won the Best Hardware Hack at Stanford TreeHacks 2021, for developing a EEG headset that allowed users to control a wheelchair.

I was awarded India’s highest civilian honour for U-18 citizens by Prime Minister Modi in 2020, for finding a method to reunite children back with their families using India's biometric-based national ID system: Aadhaar.


Selected Publications

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning
ICLR 2024 | paper | code

Dialogue Distillery: Crafting Interpolable, Interpretable, and Introspectable Dialogue from LLMs
Ryan A Chi, Jeremy Kim, Scott Hickmann, ..., Parth Sarthi, ..., Christopher D Manning
Alexa Prize SocialBot Grand Challenge | paper


Service

Reviewer for NeurIPS (2023), EMNLP (2023), ICLR (2024)


Selected Coursework

A+ in CS107 (Computer Systems), CS111 (Operating Systems), CS161 (Algorithms), CS197 (CS Research), CS236 (Deep Generative Models) among others.

CS229 (Machine Learning), CS224N (Deep Learning for NLP), CS149 (Parallel Computing), CS221 (AI Principles & Techniques), Math 53 (Differential Equations with Linear Algebra and Fourier Methods), CS255 (Cryptography)

Last Update: Jan 2024