Pierre-Yves Oudeyer
@pyoudeyer.bsky.social
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
lab, prev. @MSFTResearch @SonyCSLParis
Artificial intelligence, cognitive sciences, sciences of curiosity, language, self-organization, autotelic agents, education, AI and society
http://www.pyoudeyer.com
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
Very interesting new paper by @sucholutsky.bsky.social
Katherine Collins @norijacoby.bsky.social @billdthompson
@roberthawkins.bsky.social
arxiv.org/pdf/2506.00052
June 10, 2025 at 12:18 PM
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
Very interesting new paper by @sucholutsky.bsky.social
Katherine Collins @norijacoby.bsky.social @billdthompson
@roberthawkins.bsky.social
arxiv.org/pdf/2506.00052
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.
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.
May 28, 2025 at 2:20 PM
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.
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.
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 !👇
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 !👇
April 25, 2025 at 1:41 PM
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 !👇
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 !👇
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...
by @codingconduct.cc E. Lintunen N. Aly @creativeendvs.bsky.social
osf.io/n6x8s/downlo...
April 10, 2025 at 1:24 PM
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...
by @codingconduct.cc E. Lintunen N. Aly @creativeendvs.bsky.social
osf.io/n6x8s/downlo...
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
"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
April 3, 2025 at 9:15 AM
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
"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
A key mechanisms in human curiosity-driven exploration is the ability to assess one's own learning progress in various tasks.
Can humans predict future learning progress? When no learning has even started?
Yes, to some extent ! see this cool paper from X. Zhang, S. McDougle, and J. Leonard
Can humans predict future learning progress? When no learning has even started?
Yes, to some extent ! see this cool paper from X. Zhang, S. McDougle, and J. Leonard
March 3, 2025 at 6:07 PM
A key mechanisms in human curiosity-driven exploration is the ability to assess one's own learning progress in various tasks.
Can humans predict future learning progress? When no learning has even started?
Yes, to some extent ! see this cool paper from X. Zhang, S. McDougle, and J. Leonard
Can humans predict future learning progress? When no learning has even started?
Yes, to some extent ! see this cool paper from X. Zhang, S. McDougle, and J. Leonard
The Dynamics of Collective Creativity in Human-AI Social Networks
by S. Shiiku, R. Marjieh, M. Anglada-Tort, N. Jacoby
"...over time, hybrid human-AI networks became more diverse in their creations than AI-only networks."
📖 arxiv.org/pdf/2502.17962
by S. Shiiku, R. Marjieh, M. Anglada-Tort, N. Jacoby
"...over time, hybrid human-AI networks became more diverse in their creations than AI-only networks."
📖 arxiv.org/pdf/2502.17962
March 3, 2025 at 11:31 AM
The Dynamics of Collective Creativity in Human-AI Social Networks
by S. Shiiku, R. Marjieh, M. Anglada-Tort, N. Jacoby
"...over time, hybrid human-AI networks became more diverse in their creations than AI-only networks."
📖 arxiv.org/pdf/2502.17962
by S. Shiiku, R. Marjieh, M. Anglada-Tort, N. Jacoby
"...over time, hybrid human-AI networks became more diverse in their creations than AI-only networks."
📖 arxiv.org/pdf/2502.17962
🌍How to ground generative AI in the external world?
🤖How to turn LLMs into curious open-ended agents that spontaneously explore and set their own goals?
🤝How to align such agents on the social environment?
📺 I address these questions & our associated research program in this talk 👇
🤖How to turn LLMs into curious open-ended agents that spontaneously explore and set their own goals?
🤝How to align such agents on the social environment?
📺 I address these questions & our associated research program in this talk 👇
January 28, 2025 at 1:56 PM
🌍How to ground generative AI in the external world?
🤖How to turn LLMs into curious open-ended agents that spontaneously explore and set their own goals?
🤝How to align such agents on the social environment?
📺 I address these questions & our associated research program in this talk 👇
🤖How to turn LLMs into curious open-ended agents that spontaneously explore and set their own goals?
🤝How to align such agents on the social environment?
📺 I address these questions & our associated research program in this talk 👇