Abdellah Fourtassi

Super proud of this work and very grateful for all the amazing people who provided valuable feedback along the way @remivantrijp.bsky.social @sheinalew.bsky.social @cedricboeckx.bsky.social @inbalarnon.bsky.social ❤️❤️❤️🙏

✨ #ILCB Summer School 2025 – Just a few days to go! ✨

From September 1–5, we’ll welcome students, researchers, and lecturers at CIRM, #Marseille for a week of courses, workshops, and discussions on #language, #brain & #cognition.

Looking forward to a stimulating week of scientific exchanges!

🌞 Back from the summer break!

We kick off the new season with an exciting ILCB Talk by Simon Kirby (University of Edinburgh):

🗓️ Sept 26, 2025 – Marseille
🎙️ “Cultural evolution creates language-like structure: from humans to humpback whales and beyond”

🔗 ilcb.fr/event/simon-kirby

#ILCB

The first live session for our poster #CogSci2025 is happening right now on Teams: CogSci V3-P-41 Europe and Asia
1 august 2025
12:00 - 13:00 (GMT)
teams.microsoft.com/l/meetup-joi...
@cogscisociety.bsky.social

Let me know if you don't have access via your institution and I can send you a copy personally ☺️

Just in time for the @cogscisociety.bsky.social conference and the Rumelhart 25th Anniversary Event, the 2023 Rumelhart Prize Issue Honoring Nick Chater is out in TopiCS in Cognitive Science, edited by Mike Oaksford and me:

onlinelibrary.wiley.com/toc/17568765...

🧵 1/3

How do our brains and bodies support social learning in real time?

We take an ecological and multimodal neuroscience approach to study mutual prediction and social coordination when learning with others.

It took 5 full years for this one! Full open-access pre-print: osf.io/preprints/ps...

I am advertising 2 positions in language evolution with my group at ‪‪@dondersinst.bsky.social:
📢 Fully-funded PhD position (Robotics/AI 🤖) www.ru.nl/en/working-a...
📢 Postdoc position (Virtual Reality 🎮)
www.ru.nl/en/working-a...
Deadline for applications is August 14th. Please RT! :)

Pleased that my paper with @gabriellavigliocco.bsky.social, @fourtassi.bsky.social, Yan Gu, and Stefano James has been accepted as a talk at this year's Embodied and Situated Language Processing conference at Aix-Marseille University. Abstract below 👇

Theory: What to read The role of theory in cognitive science Or: my guide to what to read if you really want to understand how to do good, robust , theory-driven cognitive science. (disclaimer: this is an aspirational gu...

Two nice papers now added to my primer of what to read about theory in cognitive science ... docs.google.com/document/d/1... 1/

SIGdial has three fantastic keynotes this year & registration is open! 🎉

"Are there purely multi-turn 'dialog failures'?" by Dr Chris Welty

"Interactive Task Learning" by Prof Alex Lascarides

"Ecological Study of Language Acquisition, the role of natural conversation" by @fourtassi.bsky.social

Fast and robust visual object recognition in young children The visual recognition abilities of preschool children rival those of state-of-the-art artificial intelligence models.

My paper with @stellalourenco.bsky.social ‬is now out in Science Advances!

We found that children have robust object recognition abilities that surpass many ANNs. Models only outperformed kids when their training far exceeded what a child could experience in their lifetime

doi.org/10.1126/scia...

🚀 I’m excited to announce the launch of our new research chair DevAI&Speech (2025–2029), funded by the Grenoble AI Institute MIAI Cluster IA!

The project explores how human developmental processes can inspire more grounded and socially aware conversational AI (1/6).

Applications are due July 15! Spread the word 🤓🙏🏻

Bravo à Christian-G. | Inserm | Cellule Europe Bravo à Christian-G. Bénar, lauréat Inserm European Research Council (ERC) #AdvancedGrant 2024 ! 👨‍🔬 Christian-George, chercheur à l’INS - Institut de Neurosciences des Systèmes à Marseille (Inserm/A...

👏 Congratulations to Christian-G. Bénar, recipient of a 2024 ERC Advanced Grant!

He was awarded for his project OptiMEG: non-invasive recording of deep brain activity using mobile sensors optimized with intracerebral measures.

www.linkedin.com/posts/inserm...

#ERC #AdvancedGrant #amU #INS

Constructing language: A framework for explaining acquisition. New paper published by @carorowland.bsky.social‬ et al. doi.org/10.1016/j.ti....

NYU LLM + cognitive science post-doc interest form Tal Linzen's group at NYU is hiring a post-doc! We're interested in creating language models that process language more like humans than mainstream LLMs do, through architectural modifications and int...

I'm hiring at least one post-doc! We're interested in creating language models that process language more like humans than mainstream LLMs do, through architectural modifications and interpretability-style steering. Express interest here: docs.google.com/forms/d/e/1F...

Join us for this interesting discussion today! I'll contribute to the conversation on automating meaning contingency by combining methods for communicative intent tagging (e.g., question–response pairs) with tools for quantifying coherence in dialogue

Interpretability Techniques for Speech Models — Tutorial @ Interspeech 2025

The @interspeech.bsky.social early registration deadline is coming up in a few days!

Want to learn how to analyze the inner workings of speech processing models? 🔍 Check out the programme for our tutorial:
interpretingdl.github.io/speech-inter... & sign up through the conference registration form!

The first paper that discovered the spectral structure in whale codas is available here:
osf.io/preprints/os...

Text: ICIS Webinars - Thursday, June 19 2025 - Beyond Who’s Speaking When: Machine Learning Tools to Extract Rich Multi-Dimensional Features from Home Audio Recordings

Don't miss our next ICIS webinar! June 19 2025.
Join leading researchers for a deep dive into cutting-edge work in infancy research.
infantstudies.org/icis-online-...
#InfantResearch #InfantStudies

Cross-posting the abstracts for two talks I'm giving next week! This one on formal languages for LLM pretraining and evaluation, at Apple ML Research in Copenhagen on Wednesday

Following the success story of BabyBERTa, I & many other NLPers have turned to language acquisition for inspiration. In this new paper we show that using Child-Directed Language as training data is unfortunately *not* beneficial for syntax learning, at least not in the traditional LM training regime

Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models Seminal work by Huebner et al. (2021) showed that language models (LMs) trained on English Child-Directed Language (CDL) can reach similar syntactic abilities as LMs trained on much larger amounts of ...

“Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models”

I’m happy to share that the preprint of my first PhD project is now online!

🎊 Paper: arxiv.org/abs/2505.23689

🚨Job offer🚨

PhD position on my #ERC grant 'LaDy' to study how we process language in the dyad using interactive paradigms and EEG hyper-scanning.

Info and application link here (correction: application deadline is 11/07):
emploi.cnrs.fr/Offres/Docto...

@cnrs-dr12.bsky.social
@erc.europa.eu

New preprint out! 👇

We adapt the ABX task, commonly used in speech models, to investigate how multilingual text models represent form (language) vs content (meaning).

📄 arxiv.org/pdf/2505.17747

🙌 With Jie Chi, Skyler Seto, @maartjeterhoeve.bsky.social, Masha Fedzechkina & Natalie Schluter

Feature attribution is always tricky. We show just how tricky it is for speech models.

🎓⏰ Last call!

Only a few hours left to apply for the ILCB Summer School 2025 in Aix-Marseille (Sept 1–5)!

Join researchers from around the world to explore the mind & brain through lectures, courses, and discussions.

Apply now 👉 columbo.univ-amu.fr/index.php/53...

#Neuro #Ling #PhD #Postdoc

Great work and nice to see it finally out !

A schematic of our method. On the left are shown Bayesian inference (visualized using Bayes’ rule and a portrait of the Reverend Bayes) and neural networks (visualized as a weight matrix). Then, an arrow labeled “meta-learning” combines Bayesian inference and neural networks into a “prior-trained neural network”, described as a neural network that has the priors of a Bayesian model – visualized as the same portrait of Reverend Bayes but made out of numbers. Finally, an arrow labeled “learning” goes from the prior-trained neural network to two examples of what it can learn: formal languages (visualized with a finite-state automaton) and aspects of English syntax (visualized with a parse tree for the sentence “colorless green ideas sleep furiously”).

🤖🧠 Paper out in Nature Communications! 🧠🤖

Bayesian models can learn rapidly. Neural networks can handle messy, naturalistic data. How can we combine these strengths?

Our answer: Use meta-learning to distill Bayesian priors into a neural network!

www.nature.com/articles/s41...

1/n