We introduce SCRuB (Social Concept Reasoning under Rubric-Based Evaluation), a framework to measure the degree to which a model reasons about social concepts with depth and critical rigor
📄 https://t.co/EN3uvm053r <-- arxiv paper here!
*Reflections* as AI advances... I am seeing processes and systems previously established breaking down all around us; I want to see more people talking openly about this instead of just disengaging or pretending its business as usual
website here --> https://t.co/SXAIRbvKxM
Who’s Behind the Tutorial?
We have a collaboration with a great group of researchers:
Prakhar Ganesh (in person)
Carol Long
Afaf Taïk
Hsiang Hsu
Jamelle Watson-Daniels (in person)
Kathleen Creel
Flavio Calmon
Golnoosh Farnadi
Headed to Singapore for #AAAI2026 Excited to co-present our tutorial "The Many Faces of Multiplicity in ML"
Why does multiplicity matter? It helps reveal trade-offs in fairness, interpretability and reliability.
Come by!
Jan 20
2p Opal 107 | Singapore EXPO
Release Day 🎉
Meet OpenApps — a pure-Python, open-source ecosystem for stress-testing UI agents at scale.
Runs on a single CPU. Generates thousands of unique UI variations. And it reveals just how fragile today’s SOTA agents are.
(Yes, even GPT-4 and Claude struggle.)
Today we're releasing Community Alignment - the largest open-source dataset of human preferences for LLMs, containing ~200k comparisons from >3000 annotators in 5 countries / languages!
There was a lot of research that went into this... 🧵
I know internship hunting has been especially tough this year -- I hear you!
📢Great news: Our team at Microsoft Research (@MSFTResearch) has opened up a few additional internship slots for this summer! We're seeking talented PhD candidates with experience in 🖼️Multimodality, 🕹️Reinforcement Learning (RL), or 🤖Agents.
If you're interested, I'd love to connect. Please share your CV or personal website by emailing me directly at [email protected] or through DM.
Help spread the word to those still searching for internship opportunities!
In the physical world, almost all information is transmitted through traveling waves -- why should it be any different in your neural network?
Super excited to share recent work with the brilliant @mozesjacobs: "Traveling Waves Integrate Spatial Information Through Time"
1/14
📆 AFME workshop: Sat, Dec 14 in room 111-112
Excited to bring you another opportunity for insightful discussion at the AFME workshop.
💬 Join us for roundtables on Fairness/Bias Metrics and Evaluation led by the amazing @ang3linawang , @candacerossio, @tom_hartvigsen