I'm thrilled to announce that I'll join Princeton Computer Science/Princeton Center for Information Technology Policy as an assistant professor in Spring 2025 — can't wait to join this amazing group of researchers. I will continue to work on online platforms / the societal impact of AI. If you’d like to collaborate, reach out!

It was a joy to give my inaugural lecture at EPFL EPFL Computer and Communication Sciences last week. I tried to give an easy-to-digest intro into what we do at dlab (my research group), what motivates us, and why it matters, so I thought I'd share the recoding: youtube.com/watch?v=vGt0yk…

AI alignment steers AI toward human goals & values. In a recent perspective piece, we draw attention to a fundamental challenge with all such endeavors: the “AI alignment paradox”—better-aligned models are more easily misaligned. 📝arxiv.org/pdf/2405.20806 👇Example below👇

I'm excited to announce my new lab: UCSD's Learning Meaning and Natural Language Lab. a.k.a. LeM🍋N Lab! And 📢WE ARE RECRUITING📢 PhD students to join us in sunny San Diego in either Linguistics OR Data Science. Apply by Dec 4: connect.grad.ucsd.edu/apply/ More about the lab👇

Can we understand and control how language models balance context and prior knowledge? Our latest paper shows it’s all about a 1D knob! 🎛️ arxiv.org/abs/2411.07404 Co-led with Kevin Du, as well as Niklas Stoehr, Giovanni Monea, Chris Wendler, Bob West & Ryan Cotterell.

🦋Giving this a shot too: niklasstoehr

Very glad and grateful to share this fun work, especially because of the opportunity to work with this immensely talented team--Julian Minder, Niklas Stoehr, Giovanni Monea, Chris Wendler, Bob West, & Ryan Cotterell 🥳. Check it out!

📖 For our weekly MilaNLP lab seminar, it was a pleasure to have Joachim Baumann in person, introducing his work on fact-checking and music recommendation, and Niklas Stoehr giving an online talk on "Relating Items on a Shared Scale: Making Measurements with LMs." #NLProc

Very excited about this tutorial at #AAAI2025 on inducing privacy, fairness or robustness to distribution shifts when data is imperfect (e.g. unlabeled, noisy)! You can check out the slides at amartya18x.github.io/files/Tutorial…

Gemini is unstoppable! More to come!

I recently defended my PhD and moved from one dream team at ETH Zurich to another at DeepMind—a huge thank you to the many people who have supported me along the way! 🤖

Interested in shaping the progress of responsible AI and meeting leading researchers in the field? SoLaR@COLM 2025 is looking for paper submissions and reviewers! 🤖 ML track: algorithms, math, computation 📚 Socio-technical track: policy, ethics, human participant research

Gemini 🙌