@ProseMsft@5hv5hvnk@AnanyaSingha18@SumitGulwani@gustavoas@arjun_rad 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!
Checkout our team's latest research at @emnlpmeeting#EMNLP2024. If you are interested in what we do, we have various opportunities at different career stages. Find more at:
https://t.co/QGL6gYwhKC
@ProseMsft@5hv5hvnk@AnanyaSingha18@SumitGulwani@gustavoas@arjun_rad 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!
Flying to Miami tomorrow for #EMNLP2024! Excited to present two papers:
1. RAR: Retrieval Augmented Retrieval for Code Generation.
2. One-to-many Testing for Code Generation from (just) Natural Language.
Let's chat if you are interested in AI for Code or Neuro-symbolic AI!🌴✈️
⚡️The PROSE team is hiring a Senior Researcher in Bangalore, India⚡
This is an amazing opportunity to do research that will impact millions of people using Excel, Visual Studio, Power Query, and more!
https://t.co/rk85VzRSEB
It was an emotional, learning, and fun experience to put together and deliver this keynote at CAV: https://t.co/Dnlp2N8sp5
Thanks to Aarti Gupta for the souvenir pictures that capture the title and concluding remarks, without revealing the plot. Watch the talk to see who wins😊
Data scientists spend 60-80% of their time in data pre-processing. Excited to present CoWrangler, a tool that suggests data cleaning steps for your data with human-readable code! Check out our demo at @SIGMODConf🎉
Paper: https://t.co/YpBDqwOF5c
Poster: https://t.co/w6zvLH7kpf
The PROSE team is hiring Research Fellows in India to work on program synthesis⚡This is a 1-year appointment to do applied research that will impact millions of people using Excel, Visual Studio, Power Query, and more!
https://t.co/QGL6gYwPAa
We kick off day two of #SEMLA2023 with an interesting presentation on "Leveraging LLMs as Analogical Reasoning Engines to enhance Programming-by-Example (PBE) experiences" by @SumitGulwani from @MSFTResearch !
A product I worked on is released! Please try Data Wrangler for @code and let us know what you think. AI powered by @ProseMsft.
https://t.co/WXeaxEjjcU
📢 We’re excited to announce the Data Wrangler extension for VS Code Insiders. Our new, code-centric, AI-powered data cleaning/prep tool has officially previewed today! 🎉
Search "Data Wrangler" in the extension Marketplace to try it out!
Learn more at https://t.co/A55MTKx54B
We introduce FLAME, a model with only 60 million parameters for Excel formula assistance. It outperforms much larger models with billions of parameters, such as Codex-Davinci and Codex-Cushman, in several tasks for formula repair, completion, and syntax.
FLAME: A small language model for spreadsheet formulas
abs: https://t.co/tqTBzET7xW
FLAME(60M) can outperform much larger models, such as Codex-Davinci (175B), Codex-Cushman (12B), and CodeT5 (220M), in 6 out of 10 settings
There are many opportunities for AI to better support teachers and students. We aim for our research to radically improve these challenges that instructors are facing!
We ran a study to understand the pain points of CS instructors that was accepted to SIGCSE’23. Check out this summary of our findings! Collab with @smirhosseini @chrisparnin
https://t.co/382w8RBn6q
Our team's work on Excel Formula Suggestions and Formula by Examples has been featured on the @verge! (I was not personally involved)
Talk about research with large-scale impact! @ProseMsft@Microsoft@SumitGulwani
https://t.co/mKfpBxMV9c
Great @FSEconf keynote from @SumitGulwani on highly impactful research. Interesting fact: it took ~3 weeks to build the initial FlashFill research prototype, and ~2 years to make it part of Excel.