If Weapons gets noms/awards over Sinners, I will very mad…they are not even in the same league

#NewPaper A major development in the design and discovery of metal-organic frameworks (MOFs)! Thread below 👇👇👇 1/4

While I am sad to not be at #FAccT2025 in person due to last minute visa delays, I am happy to follow along virtually. Here are the slides for this morning’s presentation tinyurl.com/nteasee-facc.... Feel free to reach out for any questions. I am happy to chat about this work!

We are so proud of our ✨Honourable Mention✨ for the #FAccT2025 Best Paper Awards! This work was borne out of (com)passion, determination & a commitment to challenging norms in dataset collection & evaluation. Read more ➡️ arxiv.org/abs/2406.09496 Catch the presentation on Thurs, 11:45 local time! 🇬🇷

Looking for posts about #FAccT2025? Check out our 🦋 custom feed 🦋 which is already lively and full of papers, events, and attendees for this year's conference in Athens! Click the pin 📌 in the upper right hand corner to keep this feed quickly accessible. bsky.app/profile/mari...

Exciting update: there are multiple positions open on the Responsible AI team at GSK London UK, with a mix of applied research, foundational research and engineering. Apply here: jobs.gsk.com/en-gb/jobs/4...

Today I would like to share a journey that started 18 months ago, and while it is still ongoing, I'd like to celebrate the team's achievement of successfully having our work accepted to #FAccT2025! 🎉 🔗 arxiv.org/pdf/2406.09496

Sinners was perfect omg!! Thank you Ryan Coogler, thank you 🙏🏾 and Ludwig Göransson: you will always be goated in this house

Congrats to my co-leads @dr-nyamewaa.bsky.social, Iskandar Haykel and amazing co-authors👇🏾

Excited to share that this work will be presented at @facct.bsky.social #facct2025 🎉! Looking forward to attending my first FAccT conference and meeting the community!

AI systems present an opportunity to reflect society's biases. “However, realizing this potential requires careful attention to both technical and social considerations,” says HAI Faculty Affiliate @sanmikoyejo.bsky.social in his latest op-ed via @theguardian.com: www.theguardian.com/commentisfre...

tfw you realize how much you’ve grown when something happens and new you handles it way better than old you would have

I've recently put together a "Fairness FAQ": tinyurl.com/fairness-faq. If you work in non-fairness ML and you've heard about fairness, perhaps you've wondered things like what the best definitions of fairness are, and whether we can train algorithms that optimize for it.

#NewPaper We designed an "algorithmic microscope" & called it the Vendiscope. It is a new companion in the discovery process for scientists across fields and a powerful tool for diagnosing datasets and models for AI researchers. #AlgorithmicMicroscopy Link to paper: arxiv.org/abs/2502.10828

Congrats to @adjiboussodieng.bsky.social on being named an Early-Career Distinguished Presenter at the MRS Spring Meeting 2025! This honor is meant to highlight exciting new research directions in materials science. 🐯 #ChemScky #Princeton #VendiScoring #MatSci www.cs.princeton.edu/news/adji-bo...

I'm going to slowly repost my math notes from the other site🐦 here🦋; it's the only thing I posted over there that I think may have some long-term value & worth not deleting. These started out as notes for myself, but people seem to appreciate them. 😅 I'll keep track of all of them in this thread.

Our paper probing out-of-distribution generalization in machine learning for materials discovery is now published at Communications Materials (@NaturePortfolio) #MatSci #AI4Science #Chemsky #Vertaix 📓Link: nature.com/articles/s43...

📚 Incredible student projects from the 2024 Fall quarter's Machine Learning from Human Preferences course web.stanford.edu/class/cs329h/. Our students tackled some fascinating challenges at the intersection of AI alignment and human values. Selected project details follow... 1/n

Elphaba: but I swear someday there will be a celebration throughout Oz that’s all to do with me Me: 😬 I mean, there will be a celebration alright, but probably not the one you are imagining 👀

Ahead of the New Year, I wanted to take a moment to wish for everyone, in 2025, to have space to be themselves, time for family, friends and creativity, motivation to pursue their goals, and courage to stand out and speak up! Not to mention I hope for many laughs, and endless joy for all of us.🎉

Retweeting for myself because why do I set meetings at 9am. Why??

Okay, new years resolution. No meetings before 12. Posting this so people can yell at me when I try to schedule a meeting before then

Tons of work to do in creating vocabulary to discuss these issues so our ethics work is not just theory but can translate to practice...

Finally got around to reading this awesome paper from @adoubleva.bsky.social and this finding is really making me think...I see it in my own circles of friends/fam having an overall +ve attitude towards AI and i usually find it hard to communicate about harms/AI in my native language...

Me after NeurIPS 😂

That’s a wrap for #AFME2024!!! 🎉 Thank you to all the authors, attendees, roundtable leads and speakers for the great presentations and insightful discussions!

Our amazing panellists discussed how to define fairness and challenges of evaluation, ethical considerations and interdisciplinary collaboration for addressing different dimensions of fairness! @jessicaschrouff.bsky.social @sanmikoyejo.bsky.social @sethlazar.org Hoda Heidari

For the final contributed talk, Ben Laufer discussed the fundamental limits in the search for less discriminatory algorithms!!

Another great contributed talk!! Natalie Mackraz discussed her work on evaluating gender bias transfer between pre-trained and prompt-adapted LLMs

In the third contributed talk, Prakhar Ganesh presented his paper comparing g bias mitigation algorithms in ML!

To kick off the afternoon session, we have a great talk from @angelinawang.bsky.social on the need for group difference awareness and a new suite of benchmark for assessing this metric in LLMs!!

Ending the morning session with great discussions at the roundtables 🎊 See you after lunch

In the last invited talk of the morning, we have @sethlazar.org giving an insightful talk on evaluating the ethical competence of LLMs!!

The second contributed talk at #AFME2024. To Eun Kim discussed his paper “Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation”

Our first contributed talk is by Alex Tamkin presented his work on Evaluating and Mitigating Discrimination in Language Model Decisions!

Another great talk of the day by @krvarshney.bsky.social discussing his work on building harm detectors and guardian models for large generative models! He also addressed the need to broaden the dimensions of harms in different use cases

Great first talk by Hoda, giving an overview of fairness metrics in traditional fairness and generative models. She discussed the desiderata for a Good Measurement and steps towards building contextually aware fairness metrics in LLMs!

Off to a great start with the opening remarks by @nandofioretto.bsky.social on why this year’s topic.

It's time for our #NeurIPS2024 Algorithmic Fairness Workshop #AFME2024 🥳! Join us TODAY for a full day of discussions on fairness metrics & evaluation. Schedule: afciworkshop.org/schedule ⏰ We start at 9 am with the opening remarks, followed by a keynote by on Fairness Measurement by Hoda Heidari

Heads up: Will be live tweeting the workshop

Check out our latest work on Contextual Evaluation of Large Language Models for Tropical and Infectious Diseases (openreview.net/forum?id=yXe...), accepted at two NeurIPs workshops: GenAI4health (genai4health.github.io) and AIM-FM (aim-fm-24.github.io/NeurIPS/). #llms #genai4health #globalhealth

Not to offend anyone but risotto is really the poor man’s mbakhal. What is this 😭 If you like risotto, please go to a Senegalese restaurant and order mbakhal. It will change your life

📆AFME workshop: Sat, Dec 14 in room 111-112 My favorite part of the workshop 🥳 💬 Join our amazing leads* at the roundtables for insightful discussions on Fairness/Bias Metrics and Evaluation. * @angelinawang.bsky.social, Candace Ross (FAIR), Tom Hartvigsen (UofVirginia)

Looking forward to attending #Neurips2024 this week! Catch me at the Black in AI workshop tomorrow! I will be at the Research mentorship session! Come and chat (Why is there no neurips mug this year? 😭)

📆 AFME workshop: Sat, Dec 14 in room 111-112 Join our expert panellists* for a timely discussion on “Rethinking fairness in the era of large language models”!! * @jessicaschrouff.bsky.social, @sethlazar.org, Sanmi Koyejo, Hoda Heidari

Our @adjiboussodieng.bsky.social was one of the panelists discussing AI and Climate during Princeton's Andlinger Center's annual meeting. You can find a nice article summarizing this exciting event below: acee.princeton.edu/acee-news/an... #AI4Science #ClimateSky #Climate #Vertaix

📣 📣 Interested in an internship on human-centred AI, human agency, AI evaluation & the impacts of AI systems? Our team/FATE MLT (Su Lin Blodgett, @qveraliao.bsky.social & I) is looking for a few summer interns 🎉 Apply by Jan 10 for full consideration: jobs.careers.microsoft.com/global/en/jo...