Harshit

Harshit

Harshit Joshi

josharshit [at] gmail [dot] com

Harshit Joshi
Stanford, CA, US

I’m a first-year CS PhD student at Stanford University with the StanfordNLP group. I completed my Bachelors in IT and Mathematics from Cluster Innovation Centre, University of Delhi in 2021. I’m broadly interested in working on Neuro-symbolic Workflows for LLMs, Natural Language Processing and it’s applications in Conversational Assistants and Computational Social Science.

Previously, I was a Research Fellow at Microsoft Research with the PROSE group, where I worked on Program Repair and Formula Intelligence in Excel spreadsheets, advised by Dr. José Cambronero and Dr. Vu Le. I have been a Research Software Engineer at Supedio GmbH working on Master Data Management, Medical Entity Resolution and Text Extraction from PDFs. I have interned with the research team at DRDO, Govt. of India, where I worked on an Image Segmentation task in a simulated Gazebo environment. I spent a summer at Chennai Mathematical Institute as a Mathematical Finance Summer Scholar, working on sliding-window approaches for finding abnormal rate of returns. I have also interned with the Data Science team at Cronycle Ltd., UK, building a production-ready RSS aggregating pipeline. In the summer of 2018, I was a student developer with Google Summer of Code.

I have also had the good fortune to work with Prof. Monica Lam, Prof. Diyi Yang, Dr. Sumit Gulwani, Dr. Aditya Kanade, Dr. Rajiv Ratn Shah, Dr. Lucie Flek and Dr. Alicia Nobles.

News (older)

Jan 6, 2024 I am rotating with Prof. Diyi Yang for the winter quarter (W ‘24) in the Social And Language Technologies (SALT) Lab!
Dec 9, 2023 One of my final works at Microsoft, FLAME: A small language model for spreadsheet formulas, got accepted as Oral presentation (top ~2%) to AAAI Conference on Artificial Intelligence 2024!
Sep 21, 2023 I am rotating with Prof. Monica Lam in the Fall Quarter (F ‘23), working with Open Virtual Assistant Lab (OVAL).
May 10, 2023 I will be joining Stanford University 🌲 for PhD in Computer Science this fall (‘23) !!!!
Feb 7, 2023 Our latest work on LLMs, FLAME: A small language model for spreadsheet formulas, was on the front page of HackerNews and covered by media outlets (TheRegister, techradar)

Selected Publications (all)

(*: Equal Contribution)
  1. FLAME: A small language model for spreadsheet formulas
    Joshi, Harshit, Ebenezer, Abishai, Cambronero, José, Gulwani, Sumit, Kanade, Aditya, Le, Vu, Radiček, Ivan, and Verbruggen, Gust
    Proceedings of the AAAI Conference on Artificial Intelligence, 38 2023
  2. Repair Is Nearly Generation: Multilingual Program Repair with LLMs
    Joshi, Harshit, Cambronero, José, Gulwani, Sumit, Le, Vu, Radicek, Ivan, and Verbruggen, Gust
    Proceedings of the AAAI Conference on Artificial Intelligence, 37 2023
  3. Neurosymbolic Repair for Low-Code Formula Languages
    Bavishi, Rohan*, Joshi, Harshit*, Sánchez, José Pablo Cambronero, Fariha, Anna, Gulwani, Sumit, Le, Vu, Radicek, Ivan, and Tiwari, Ashish
    In Proceedings of the ACM on Programming Languages (OOPSLA2) 2022

Current and Past Affiliations