Seriously, it would be difficult to find better opportunities than the one that involves Excel, Python, and AI. Andy Gordon's team is well-connected with the Excel product group and also collaborates with several other research teams including ours. Consider applying!

Ever wondered how to select the most relevant examples for your NL to Code tasks using LLMs? Check out: TSTr: Target Similarity Tuning in the Real world. (Accepted to EMNLP-Findings 2023) Sumit Gulwani, Vu Le, Gust Verbruggen, Priyanshu Gupta, Mukul Singh, Ananya Singha [1/3]

We are revolutionizing the debugging experience within VS, now supercharged by GitHub Copilot. Copilot's enhanced debugging capabilities were showcased at #MSIgnite last week. Do check this out & share your feedback with us! Microsoft PROSE Team Gustavo Soares Arjun Radhakrishna Sumit Gulwani

We are making data manipulation easy and fun with the new Copilot. Check out and share your experience :D Microsoft PROSE Team Anirudh Khatry Gust Verbruggen Sumit Gulwani

Our recent work at Microsoft PROSE Team around Improving Debugging conversations in Microsoft Visual Studio Copilot through conversation analysis got featured in the Microsoft Research blog. Sounds interesting? Here's the arxiv: arxiv.org/abs/2402.06229 Bhavya Chopra Gustavo Soares Arjun Radhakrishna Sumit Gulwani

Ever wish you could uncover data insights with just a snap of your fingers? 🤔 Say hello to automated insights – making data exploration a breeze! (1/7) #DataScience #AI #InsightAutomation

Our work on “Semantically Aligned Question and Code Generation for Automated Insight Generation” was covered by the latest edition of Microsoft Research Focus! Ananya Singha Bhavya Chopra Sumit Gulwani Austin Henley Gust Verbruggen Mukul Singh Chris Parnin & Vu Le!

New preprint An Empirical Study of Validating Synthetic Data for Formula Generation (arxiv.org) TL; DR: This paper empirically evaluates the impact of three validation techniques that check accuracy of synthetic NL instructions for spreadsheet formula generation.

Our work on debugging with GitHub Copilot Chat won Best Paper Award at VL/HCC! We introduce ROBIN, an “investigate & respond” agentic LLM workflow. As we approach a balance b/w automation vs. collaboration, we observe 3.5x greater bug fixes! 🤖 📜Paper: microsoft.com/en-us/research…

So true!

Excited to see Metareflection - our EMNLP'24 paper on improving language agents, featured in Research Focus!

Microsoft PROSE Team Shashank Kirtania @ ICLR Ananya Singha Sumit Gulwani Gustavo Soares Arjun Radhakrishna I am attending EMNLP🌴in-person at Miami, to present MetaReflection. Please drop by at the Riverfront Hall at the 11AM Poster session on Nov 13th (today!) to know more about it or chat about Language agents and Neuro-symbolic AI at large!

Dr. Sumit Gulwani, our Distinguished Alumnus Awardee 2024, expresses his joy in reliving the nostalgic days by walking the halls and walkways of the campus. Listen to his insights on the future of AI technology and the importance of giving back. #LegendsofIITK #IITKAlumni

Great talk by Sumit Gulwani (Sumit Gulwani, Microsoft) on improving AI reasoning by using intent, interaction, inspection, and memory (see last picture) at #KDD2025 in Toronto, Canada. #AI #LLM #CodeGeneration

"How I became a story teller?" by Sumit Gulwani at Microsoft Research is one of the most useful talk I ever watched. This will for sure lead me to improving my public speaking skills. Thank you Sumit! youtube.com/watch?v=ur_YQp…