←
Emre Kıcıman1,921 posts
Emre Kıcıman avatar

Emre Kıcıman

@emrek

causal ml; ai+society; social media, comp social science. having fun. sr principal researcher @MSFTResearch. my opinions. he/him. hci.social/@emrek

◷ Joined May 2008▧ 87 Photos and videos
Emre Kıcıman avatar
Emre Kıcıman@emrek·31 May 2022

Hey #CausalTwitter, some news about our DoWhy python library - we are excited by how people are using DoWhy and we are working to support a broader community!

To broaden access to this important causal library—widely used with 1M+ downloads—DoWhy is moving to an independent PyWhy GitHub organization. The first step: collaboration with @awscloud, which is contributing advanced graphical causal model algorithms: msft.it/6010bVMDm

Koustuv Saha avatar
⟳ Emre Kıcıman retweeted
Koustuv Saha@kous2v·26 Apr 2024

Happy that our #CHI2024 paper on the observer effect received an honorable mention award! 🏆 One of my favorite papers, and it was a joyful journey to do this work ❤️ Thanks again to my amazing coauthors @Pranshu258 @GloriaMark_PhD @emrek @munmun10 tinyurl.com/chi24obs

We often wonder how the awareness of being "watched" affects our online behaviors. Our #CHI2024 paper studies observer (/hawthorne) effect: how do people's social media use deviate from typical use with the awareness of being observed? w/ Pranshu @emrek @GloriaMark_PhD @munmun10

Post attachment
Emre Kıcıman avatar
⟳ Emre Kıcıman retweeted
Emre Kıcıman@emrek·7 Feb 2024

Excited to release the AI Controller Interface, making it easier to tightly integrate and experiment with new strategies for controlling #LLM generation with custom logic, data, constrained decoding, parallel generations, ... cc: @m_moskal

The AI Controller Interface helps researchers and developers to efficiently implement existing strategies for controlling LLMs and invent new ones, enhancing LLM generation through improved accuracy, privacy, and compliance with formatting standards. msft.it/6011i71u1

tobi lutke avatar
⟳ Emre Kıcıman retweeted
tobi lutke@tobi·11 Mar 2024

This is actually brilliant work by microsoft: github.com/microsoft/aici. Sending mini WASM programs instead of prompts to LLM providers would be incredibly powerful. Multiturn, , Grammar, COT, RAG, function calling, etc could all massively benefit from this

Aniket Vashishtha avatar
⟳ Emre Kıcıman retweeted
Aniket Vashishtha@AniketVashisht8·27 Feb 2024

Had a great time presenting our work on causal inference! Thanks for the opportunity to interact with other researchers producing such interesting work on utilising LLMs for causal reasoning! #AAAI24 Work done at @MSFTResearch

This tweet is unavailable

Emre Kıcıman avatar
Emre Kıcıman@emrek·26 Feb 2024

Had a great conversation with @AleksanderMolak today and am looking forward to the causality and LLMs AAAI workshop on Tuesday!

This tweet is unavailable

Emre Kıcıman avatar
Emre Kıcıman@emrek·25 Feb 2024

If you’re enjoying the #aaai panel on llms right now, check out this panel on current challenges with llms coming up at 6:30pm this evening

At AAAI in Vancouver this week? Make sure to check out the CLEI 2024 industry panel, where we discuss current challenges in commercializing LLMs. When? Saturday 6:30pm. Sign up here: aaaipanel.rsvpify.com/

Post attachment
Patrick Huber avatar
⟳ Emre Kıcıman retweeted
Patrick Huber@huberpa91·23 Feb 2024

At AAAI in Vancouver this week? Make sure to check out the CLEI 2024 industry panel, where we discuss current challenges in commercializing LLMs. When? Saturday 6:30pm. Sign up here: aaaipanel.rsvpify.com/

Post attachment
🔥囧Robert Osazuwa Ness囧🔥 avatar
⟳ Emre Kıcıman retweeted
🔥囧Robert Osazuwa Ness囧🔥@osazuwa·7 Feb 2024

Causal AI is a practical introduction to building AI models that can reason about causality. Author Robert Ness, a leading researcher in causal AI at Microsoft Research, brings his unique expertise to this cutting-edge guide. Available at manning.com

Post attachment