I'm very happy to give a spotlight at the Mechanistic Interpretability Workshop @ ICML on our work: "Validating Causal Abstraction Metrics on Simulated Complex Systems" Which metrics actually tell you if an explanation is valid? We built a benchmark to find out. 1/n

New preprint: The Dead Salmons of XAI Standard fMRI pipelines once detected predictive brain regions in a dead salmon! A warning about poor statistical methodology Now, XAI faces its own issues: many methods can yield plausible explanations even for randomized networks arxiv.org/abs/2512.18792

The Dead Salmons of AI Interpretability

In a striking neuroscience study, the authors placed a dead salmon in an MRI scanner and showed it images of humans in social situations. Astonishingly, standard analyses of the time reported brain re...

arxiv.org

I'm recruiting multiple PhD students for Fall 2026 in Computer Science at @hopkinsengineer.bsky.social 🍂 Apply to work on AI for social sciences/human behavior, social NLP, and LLMs for real-world applied domains you're passionate about! Learn more at kristinagligoric.com & help spread the word!

I'm very happy to present our work "Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?" this afternoon at #ICLR2025! Come have a chat at stand #439 :)

Our paper "Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?" will be presented at #ICLR2025! It's also the first paper of my first PhD student, congrats @maximemeloux.bsky.social ! 🎉 blog: melouxm.github.io/MI-identifia... An explanatory thread 🧵:

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc. Details in 🧵

bc i haven't done so yet, i decided to burn any remaining bridge to the land of statistics. it wasn't statisticians nor statistics but it was me. i am simply not good enough to do statistics myself. so, @peyrardmax.bsky.social and i decided to turn statistical estimation into supervised learning.

Check out our new paper on social determinants of on-campus food choice, now out in @pnasnexus.org! academic.oup.com/pnasnexus/ar...

PNAS Nexus@pnasnexus.org · 2y ago

To nudge people to eat better, it helps to understand what shapes food choices. A study of 18 million purchases at a canteen at @icepfl.bsky.social shows that after a person selects an item, the next person in line is more likely to choose the same item. PNAS Nexus: academic.oup.com/pnasnexus/ad...

I tried to find everyone who works in the area but I certainly missed some folks so please lmk... go.bsky.app/BYkRryU