Harshit Joshi Photo

Harshit Joshi

Stanford, CA

twitter | google scholar | linkedin | github

About

I'm a second-year CS PhD student at Stanford University with the StanfordNLP group and OVAL lab, advised by Monica Lam. I'm currently interested in creating useful systems that assist users to leverage capabilities of Large Language Models for gathering and creating knowledge.


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 José Cambronero and 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. In the summer of 2018, I was a student developer with Google Summer of Code.


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

Recent Publications [all]

Publication Image

Coding Reliable LLM-based Integrated Task and Knowledge Agents with GenieWorksheets

Harshit Joshi, Shicheng Liu, James Chen, Robert Weigle, Monica S Lam, 2024
Publication Image

FLAME: A small language model for spreadsheet formulas

Harshit Joshi, Abishai Ebenezer, José Cambronero Sanchez, Sumit Gulwani, Aditya Kanade, Vu Le, Ivan Radiček, Gust Verbruggen, 2024
Publication Image

Repair Is Nearly Generation: Multilingual Program Repair with LLMs

Harshit Joshi, José Cambronero Sanchez, Sumit Gulwani, Vu Le, Gust Verbruggen, Ivan Radiček, 2023

News

Contact

Email: harshitj [at] cs [dot] stanford . edu

Twitter: @harshitj__