Pierre-Yves Oudeyer
@pyoudeyer.bsky.social
390 followers 450 following 49 posts
Research director @Inria, Head of @flowersInria lab, prev. @MSFTResearch @SonyCSLParis Artificial intelligence, cognitive sciences, sciences of curiosity, language, self-organization, autotelic agents, education, AI and society http://www.pyoudeyer.com
Posts Media Videos Starter Packs
pyoudeyer.bsky.social
Major new system and result from the team: SOAR is an open-source self-improving genAI system pushing the frontier of ARC performances using program synthesis

It relies on using LLMs as self-improving smart operators for evolutionary search
jul-p.bsky.social
Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #ICML!)

It brings LLMs from just a few percent on ARC-AGI-1 up to 52%

We’re releasing the finetuned LLMs, a dataset of 5M generated programs and the code.

🧵
pyoudeyer.bsky.social
Congratulations @jul-p.bsky.social for this major achievement and @ccolas.bsky.social for the amazing co-supervision ! Your work was magic to develop this self-improving system pushing the frontier of what can be done with program synthesis and open-source methods and models on the ARC challenge !
pyoudeyer.bsky.social
Using LLMs to advance the cognitive science of collectives

Very interesting new paper by @sucholutsky.bsky.social
Katherine Collins @norijacoby.bsky.social @billdthompson
@roberthawkins.bsky.social

arxiv.org/pdf/2506.00052
Reposted by Pierre-Yves Oudeyer
enroweb.com
Le travail de Samuel Bianchini à partir des algorithmes de @pyoudeyer.bsky.social mis en lumière par le Jeu de paume dans son expo IA
Catalogue de l’expo « Le monde selon l’IA » Artiste et enseignant-chercheur, Samuel Bianchini collabore avec de nombreux ingénieurs et scientifiques pour explorer les relations qu'entretiennent les nouvelles technologies avec les contextes culturels dans lesquels elles s'insèrent.
Dans cette troisième version de l'installation Prendre vie(s), Samuel Bianchini mobilise Flow Lenia, un logiciel de vie artificielle augmentee par IA. Cette forme d'animation, née d'une simulation mathématique appelée «jeu de la vie » en 1970, compose des systèmes susceptibles d'adopter des comportements émergents et inattendus.

Prendre vie(s), version 03, 2020-2025
Développement informatique (algorithmes de vie et d'intelligence artificielles):
Léon Denise et Adrian Mangel, sur la base de l'environnement logiciel Flow Lenia développé par l'équipe Flowers (Inris.
Université de Bordeaux - Pierre-Yves
Oudeyer, Clément Moulin-Fricr, Gautier Hamon et Erwan Plantee) à partir de Lenis. développé par Bert Chan (DeepMind). et avec la collaboration de Colin Bouvry Ce projet a bénéficié du soutien de l'École des arts décoratifs (Université PSL, Paris) et du festival accès)s( cultures électroniques
Remerciements: Alain Declercq.
Jean-Jacques Gay. Stéphane Trois Carrés
pyoudeyer.bsky.social
Humans' ability to invent their own games & goals is at the core of open-ended learning.

Understanding and modeling computationally how they do it would be enlightening to understand better human cognition and build open-ended AI

Great step in this direction in new paper by Guy Davidson et al.
Reposted by Pierre-Yves Oudeyer
melaniemitchell.bsky.social
I reviewed "These Strange New Minds: How AI Learned to Talk and What It Means" by Chris Summerfield.

melaniemitchell.me/EssaysConten...
pyoudeyer.bsky.social
Cool
lisyarus.bsky.social
Published my WebGPU Particle Life simulation online! Obviously it requires WebGPU support, and it's quite resource-demanding, so I've set the particle count to 64k for now. Also it probably doesn't work on mobile; will fix later.

Enjoy: lisyarus.github.io/webgpu/parti...
Particle Life 2D
lisyarus.github.io
Reposted by Pierre-Yves Oudeyer
Reposted by Pierre-Yves Oudeyer
mcvjetko.bsky.social
Here is a cool Flow-Lenia simulation, which is a continuous cellular automaton with two distinct features:
1. Mass conservation - sum of all activations is constant through time
2. Localized update rules - enables simulations with differently behaving matter on the same grid
Reposted by Pierre-Yves Oudeyer
clemmoulinfrier.bsky.social
Very happy that our paper received both the EvoApps best paper and the EvoStar best student paper! Congrats team!!

Emergent Kin Selection of Altruistic Feeding via Non-Episodic Neuroevolution
arxiv.org/abs/2411.10536
Reposted by Pierre-Yves Oudeyer
stepalminteri.bsky.social
Check out @nicolasyax.bsky.social
thread about our paper (co-supervised by @pyoudeyer.bsky.social) where we show that evolutionary tree reconstruction can be successfully applied to map LLMs to map relations and predict their performance! Currently at @iclr-conf.bsky.social
pyoudeyer.bsky.social
And thank you @gaiamolinaro.bsky.social for presenting the work ! + thanks Jérémy Perez for leading the project and thanks the whole team Corentin Leger
@kovacgrgur.bsky.social @ccolas.bsky.social
@clemmoulinfrier.bsky.social
@maximederex.bsky.social
pyoudeyer.bsky.social
Generative AI is a cultural transmission technology:
it plays a growing role in generation, selection and transmission of ideas/opinions in human society 🧠🔄🌐

And yet we understand very little of this dynamics at this point 🤔❓

A step forward is our #ICLR2025 paper !👇
pyoudeyer.bsky.social
@thomwolf.bsky.social This is the HF space we discussed, allowing to map the space of all models on HF, and infer which derive from where :)
pyoudeyer.bsky.social
Congratulations @nicolasyax.bsky.social for the amazing work, and @stepalminteri.bsky.social for the co-supervision !
pyoudeyer.bsky.social
I have to say that when Nicolas pitched us the idea of this project, I was excited about the creativity, but was not convinced it would work: I was completely wrong, it worked close to directly! Beautiful!
pyoudeyer.bsky.social
Imagine you can compute a (very) cheap behavioural signatures for LLMs and from it
1) infer their history (which previous models they derived from)
2) build large maps to navigate spaces of 100s of models
3) predict (coarsely) their performances in benchmarks

That's PhyloLM 🚀
nicolasyax.bsky.social
🔥Our paper PhyloLM got accepted at ICLR 2025 !🔥
In this work we show how easy it can be to infer relationship between LLMs by constructing trees and to predict their performances and behavior at a very low cost with @stepalminteri.bsky.social and @pyoudeyer.bsky.social ! Here is a brief recap ⬇️
pyoudeyer.bsky.social
We are starting a new major research project investigating the joint development of curiosity and metacognition in adolescents, where the Flowers lab will collaborate with @mjgruber.bsky.social 's lab at Univ. Cardiff, and Yana Fandakova at Univ. Trier !!! Open postdocs positions, see below 👇
mjgruber.bsky.social
Interested in curiosity and metacognition in childhood and adolescence? Join us at Cardiff University (UK) for a Postdoc position in an international collaboration with @yanafandakova.bsky.social (Germany) and @pyoudeyer.bsky.social (France). Please repost! #DevPsych #PsychSciSky #neuroskyence
Job Search | Cardiff University
Search for Internet job results.
krb-sjobs.brassring.com
pyoudeyer.bsky.social
Why Self-Determination Theory Needs Computational Modelling: The Case of Competence and Optimal Challenge

by @codingconduct.cc E. Lintunen N. Aly @creativeendvs.bsky.social

osf.io/n6x8s/downlo...
pyoudeyer.bsky.social
Thanks @ccolas.bsky.social for pointing it out ! This has great potential for diversity search algorithms
pyoudeyer.bsky.social
Forcing Diffuse Distributions out of Language Models

"When LLMs are used for real-world tasks where diversity of outputs is crucial their inability to produce
diffuse distributions over valid choices is a major hurdle"

New method to address this challenge by Zhang et al.:

arxiv.org/pdf/2404.10859