Me and Mukul Singh will be at EMNLP ‘23 ✈️! We would love to catch up and discuss the AI4Code progress that we have been doing at Microsoft PROSE Team ⚡️ Also I’ll be presenting “TSTR: Target Similarity Tuning meets the Real World” Looking forward to exciting discussions!

⚠️Emergency Reviewers⚠️ needed for #ICLR2024TinyPapers We are approaching the end of reviewing period, but sadly <50% reviewers have completed they assignment. We need emergency reviewers to review tiny (2-page!!) papers! Please reach out to iclr.dei.2023@gmail if interested!

5 hours done and 7 more to go till I make it to London! I’ll be attending POPL’24 from 14th to 20th Jan. I am super excited to discuss PL research and the synthesis work we’ve been doing at Microsoft PROSE Team! Feel free to reach out for a coffee chat!

After a quick contractor role at Boson where I worked on improving VLLM's I am in the market. I am looking for Research scientist/ Applied Researcher/ MLE roles I have trained cool models for code generation Microsoft PROSE Team and also have one pub at ICSE.

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

Excited with this opportunity! Can't wait to share insights on AI advancements, PROSE team's work, and our impact at Microsoft. See you in July at #AIware2024! 🎙️🔥

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

17-year-old Indian prodigy 🇮🇳 Gukesh D makes history as the youngest-ever player to win the #FIDECandidates! 🔥 📷 Michal Walusza

RUBICON evaluates AI-driven conversations and improves their quality by learning detailed domain-specific rubrics from minimal data. It gathers insights on AI assistant performance while maintaining user privacy and data security. msft.it/6016YFzkG

The first session at #VLHCC2024. Yasharth Bajpai discusses the Conversational Debugging with GitHub Copilot. #VLHCC2024 #ResearchTrack

🏆 Best Research Paper Award! 🏆 Huge congratulations to Yasharth Bajpai and the team, from Microsoft for their award-winning paper: "Let's Fix This Together - Conventional Debugging with GitHub Copilot." 🤖💡 Well-deserved recognition! 🎉 #VLHCC2024 #BestPaperAward

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…

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

Some very cool work happening at Microsoft PROSE Team. Do stop by if you are at EMNLP!

Saksham and I have collaborated on a few projects during our overlap at MS. He's a smart guy, with a hands-on approach and varied industry experience. Moreover, I had fun working with him :) If you are hiring PhD students in AI4Code/SE, do consider him!

Check out this cool piece of work on enabling agentic spreadsheet scaffolding, done at Microsoft PROSE Team! Kudos to Jenny Liang & Aayush for leading this effort.