Pierre-Yves Oudeyer
@pyoudeyer
Research director @inria, Head of @flowersInria lab, prev. @MSFTResearch @SonyCSLParis https://www.linkedin.com/in/pierreyvesoudeyer/ http://pyoudeyer.bsky.social
🌍How to ground generative AI in the external world? 🤖How to turn LLMs into curious agents that spontaneously explore, set their own goals, and become open-ended learners? 🤝How to align such agents on the social environment? 📺In this talk, I outline a research program I…
We are hosting a student researcher for the end of the year with @eyvindn and others in the PI team (github.com/paradigms-of-i…) ✨ If you are interested in pushing forward NCA research or explore computational life🦎👾, be sure to fill out the form!
looking for a student researcher September-December. working w/ me+@mayalen_etc, and alongside @zzznah+@RandazzoEttore+others in Pi, on either NCAs or Computational Life. must be enrolled in a degree granting program. fill out the interest form by EOW: docs.google.com/forms/d/e/1FAI…
New blog post ! What if LLM agents could learn by doing, not just by reading? 🤔 2024 was the year of "agentic AI"—systems that plan, act, and execute complex workflows autonomously. But current agents face critical limitations... 🧵
With the right UX this could be the basis for a really fun and unique game. Code is available!
Synthetic ecosystems that autonomously and continuously evolve in silico 👾 An Alifer dream we pursue with Flow-Lenia ! If you are interested in complex systems with (1) emergent creatures and (2) intrinsic evolutionary dynamics, go check our new paper ! A 🧵
New paper in the Alife journal ! Flow-Lenia: Emergent Evolutionary Dynamics in Mass Conservative Continuous Cellular Automata Congratulations @eplantec and amazing team !
Synthetic ecosystems that autonomously and continuously evolve in silico 👾 An Alifer dream we pursue with Flow-Lenia ! If you are interested in complex systems with (1) emergent creatures and (2) intrinsic evolutionary dynamics, go check our new paper ! A 🧵
🌍 Imagine transforming an LLM into a curiosity-driven AI scientist that generates theories and makes experiments to test them: This is WorldLLM! 🔬 ▶️ Check our new RLDM paper below 👇
I'll be at RLDM this week to present our new paper: WorldLLM 😃 In the same spirit as our previous works — e.g. GLAM, MAGELLAN... — which investigate how to ground LLMs through interactions with external environments, WorldLLM takes a deep dive into the world modeling aspect.
new paper: "Evolution and the Knightian Blindspot of Machine Learning" Our ever-changing world bubbles with surprise and complexity. General AI must include handling unforeseen situations with grace. Yet this issue largely lies outside AI's formalisms: a blind spot. (1/n)
Using LLMs to advance the cognitive science of collectives Very interesting new paper by @sucholutsky Katherine Collins @norijacoby @billdthompson Robert Hawkins arxiv.org/pdf/2506.00052
. @khoomeik here are several papers on curiosity-driven LLM agents: - MAGELLAN (ICML 2025): arxiv.org/abs/2502.07709 - ACES (Neurips 2024): proceedings.neurips.cc/paper_files/pa… - LMA3: proceedings.mlr.press/v232/colas23a.… @cedcolas - Perspective and history (before 2010s :)): nature.com/articles/s4225…