Gaia Molinaro

Senior Applied Scientist

Publications

View by:

- Language model goal selection differs from humans’ in a self-driven learning task
  
  Gaia Molinaro, Dave August, Danielle Perszyk, Anne G. E. Collins
  
  NeurIPS | December 2026, Vol 39
  
  Publication
- Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science
  
  Gaia Molinaro, Anne G. E. Collins, Pierre-Yves Oudeyer, Cédric Colas
  
  Current Opinion in Behavioral Sciences | September 2026
  
  Publication
- Investigating the role of task representation switch costs in goal persistence
  
  Gaia Molinaro, Aly Lidayan, Anne G. E. Collins
  
  CogSci | July 2026, Vol 48: pp. 1409-1416
  
  Publication
- The Cultural Evolution of Human Goals
  
  Jérémy Perez, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Maxime Derex, Clément Moulin-Frier
  
  Topics in Cognitive Science | July 2026
  
  Publication
- When 0 is good: instrumental learning with counterintuitive goals decreases working memory engagement
  
  Ti-Fen Pan, Gaia Molinaro, Anne G. E. Collins
  
  CogSci | July 2025, Vol 47: pp. 643-649
  
  Publication
- Spontaneous thought as play: the value of fictional goals in the default mode network
  
  Gaia Molinaro, Moshe Bar
  
  Current Opinion in Behavioral Sciences | June 2025, Vol 63: pp. 101504
  
  Publication
- When LLMs play the telephone game: Cumulative changes and attractors in iterated cultural transmissions
  
  Jérémy Perez, Grgur Kovač, Corentin Léger, Cédric Colas, Gaia Molinaro, Maxime Derex, Pierre-Yves Oudeyer, Clément Moulin-Frier
  
  ICLR | April 2025
  
  Publication
- ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
  
  Julien Pourcel, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Laetitia Teodorescu
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- Latent learning progress drives autonomous goal selection in human reinforcement learning
  
  Gaia Molinaro, Cédric Colas, Pierre-Yves Oudeyer, Anne G. E. Collins
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- What should I do now? Goal-centric outlooks on learning, exploration, and communication
  
  Cédric Colas, Junyi Chu, Gaia Molinaro, Robert Hawkins
  
  CogSci | July 2024, Vol 46: pp. 24-25
  
  Publication
- A goal-centric outlook on learning
  
  Gaia Molinaro, Anne G. E. Collins
  
  Trends in Cognitive Sciences | December 2023, Vol 27(12): pp. 1150–1164
  
  Publication
- Multifaceted information-seeking motives in children
  
  Gaia Molinaro, Irene Cogliati Dezza, Sarah Katharina Bühler, Christina Moutsiana, Tali Sharot
  
  Nature Communications | September 2023, Vol 14(1): pp. 5505
  
  Publication
- A reinforcement learning framework for information-seeking and information-avoidance
  
  Irene Cogliati Dezza, Gaia Molinaro, Tom Verguts
  
  CogSci | July 2023, Vol 45
  
  Publication
- Human hacks and bugs in the recruitment of reward systems for goal achievement
  
  Gaia Molinaro, Anne G. E. Collins
  
  CogSci | July 2023, Vol 45
  
  Publication
- Intrinsic rewards explain context-sensitive valuation in reinforcement learning
  
  Gaia Molinaro, Anne G. E. Collins
  
  PLOS Biology | July 2023, Vol 21(7): pp. e3002201
  
  Publication

- Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science
  
  Gaia Molinaro, Anne G. E. Collins, Pierre-Yves Oudeyer, Cédric Colas
  
  Current Opinion in Behavioral Sciences | September 2026
  
  Publication
- Investigating the role of task representation switch costs in goal persistence
  
  Gaia Molinaro, Aly Lidayan, Anne G. E. Collins
  
  CogSci | July 2026, Vol 48: pp. 1409-1416
  
  Publication
- The Cultural Evolution of Human Goals
  
  Jérémy Perez, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Maxime Derex, Clément Moulin-Frier
  
  Topics in Cognitive Science | July 2026
  
  Publication
- When 0 is good: instrumental learning with counterintuitive goals decreases working memory engagement
  
  Ti-Fen Pan, Gaia Molinaro, Anne G. E. Collins
  
  CogSci | July 2025, Vol 47: pp. 643-649
  
  Publication
- Spontaneous thought as play: the value of fictional goals in the default mode network
  
  Gaia Molinaro, Moshe Bar
  
  Current Opinion in Behavioral Sciences | June 2025, Vol 63: pp. 101504
  
  Publication
- Latent learning progress drives autonomous goal selection in human reinforcement learning
  
  Gaia Molinaro, Cédric Colas, Pierre-Yves Oudeyer, Anne G. E. Collins
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- What should I do now? Goal-centric outlooks on learning, exploration, and communication
  
  Cédric Colas, Junyi Chu, Gaia Molinaro, Robert Hawkins
  
  CogSci | July 2024, Vol 46: pp. 24-25
  
  Publication
- A goal-centric outlook on learning
  
  Gaia Molinaro, Anne G. E. Collins
  
  Trends in Cognitive Sciences | December 2023, Vol 27(12): pp. 1150–1164
  
  Publication
- Multifaceted information-seeking motives in children
  
  Gaia Molinaro, Irene Cogliati Dezza, Sarah Katharina Bühler, Christina Moutsiana, Tali Sharot
  
  Nature Communications | September 2023, Vol 14(1): pp. 5505
  
  Publication
- A reinforcement learning framework for information-seeking and information-avoidance
  
  Irene Cogliati Dezza, Gaia Molinaro, Tom Verguts
  
  CogSci | July 2023, Vol 45
  
  Publication
- Intrinsic rewards explain context-sensitive valuation in reinforcement learning
  
  Gaia Molinaro, Anne G. E. Collins
  
  PLOS Biology | July 2023, Vol 21(7): pp. e3002201
  
  Publication
- Human hacks and bugs in the recruitment of reward systems for goal achievement
  
  Gaia Molinaro, Anne G. E. Collins
  
  CogSci | July 2023, Vol 45
  
  Publication
- Language model goal selection differs from humans’ in a self-driven learning task
  
  Gaia Molinaro, Dave August, Danielle Perszyk, Anne G. E. Collins
  
  NeurIPS | December 2026, Vol 39
  
  Publication
- Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science
  
  Gaia Molinaro, Anne G. E. Collins, Pierre-Yves Oudeyer, Cédric Colas
  
  Current Opinion in Behavioral Sciences | September 2026
  
  Publication
- When LLMs play the telephone game: Cumulative changes and attractors in iterated cultural transmissions
  
  Jérémy Perez, Grgur Kovač, Corentin Léger, Cédric Colas, Gaia Molinaro, Maxime Derex, Pierre-Yves Oudeyer, Clément Moulin-Frier
  
  ICLR | April 2025
  
  Publication
- Latent learning progress drives autonomous goal selection in human reinforcement learning
  
  Gaia Molinaro, Cédric Colas, Pierre-Yves Oudeyer, Anne G. E. Collins
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
  
  Julien Pourcel, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Laetitia Teodorescu
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- Language model goal selection differs from humans’ in a self-driven learning task
  
  Gaia Molinaro, Dave August, Danielle Perszyk, Anne G. E. Collins
  
  NeurIPS | December 2026, Vol 39
  
  Publication
- ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
  
  Julien Pourcel, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Laetitia Teodorescu
  
  NeurIPS | December 2024, Vol 37
  
  Publication

- Language model goal selection differs from humans’ in a self-driven learning task
  
  Gaia Molinaro, Dave August, Danielle Perszyk, Anne G. E. Collins
  
  NeurIPS | December 2026, Vol 39
  
  Publication
- Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science
  
  Gaia Molinaro, Anne G. E. Collins, Pierre-Yves Oudeyer, Cédric Colas
  
  Current Opinion in Behavioral Sciences | September 2026
  
  Publication
- Investigating the role of task representation switch costs in goal persistence
  
  Gaia Molinaro, Aly Lidayan, Anne G. E. Collins
  
  CogSci | July 2026, Vol 48: pp. 1409-1416
  
  Publication
- The Cultural Evolution of Human Goals
  
  Jérémy Perez, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Maxime Derex, Clément Moulin-Frier
  
  Topics in Cognitive Science | July 2026
  
  Publication
- When 0 is good: instrumental learning with counterintuitive goals decreases working memory engagement
  
  Ti-Fen Pan, Gaia Molinaro, Anne G. E. Collins
  
  CogSci | July 2025, Vol 47: pp. 643-649
  
  Publication
- Spontaneous thought as play: the value of fictional goals in the default mode network
  
  Gaia Molinaro, Moshe Bar
  
  Current Opinion in Behavioral Sciences | June 2025, Vol 63: pp. 101504
  
  Publication
- When LLMs play the telephone game: Cumulative changes and attractors in iterated cultural transmissions
  
  Jérémy Perez, Grgur Kovač, Corentin Léger, Cédric Colas, Gaia Molinaro, Maxime Derex, Pierre-Yves Oudeyer, Clément Moulin-Frier
  
  ICLR | April 2025
  
  Publication
- Latent learning progress drives autonomous goal selection in human reinforcement learning
  
  Gaia Molinaro, Cédric Colas, Pierre-Yves Oudeyer, Anne G. E. Collins
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
  
  Julien Pourcel, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Laetitia Teodorescu
  
  NeurIPS | December 2024, Vol 37
  
  Publication
- What should I do now? Goal-centric outlooks on learning, exploration, and communication
  
  Cédric Colas, Junyi Chu, Gaia Molinaro, Robert Hawkins
  
  CogSci | July 2024, Vol 46: pp. 24-25
  
  Publication
- A goal-centric outlook on learning
  
  Gaia Molinaro, Anne G. E. Collins
  
  Trends in Cognitive Sciences | December 2023, Vol 27(12): pp. 1150–1164
  
  Publication
- Multifaceted information-seeking motives in children
  
  Gaia Molinaro, Irene Cogliati Dezza, Sarah Katharina Bühler, Christina Moutsiana, Tali Sharot
  
  Nature Communications | September 2023, Vol 14(1): pp. 5505
  
  Publication
- A reinforcement learning framework for information-seeking and information-avoidance
  
  Irene Cogliati Dezza, Gaia Molinaro, Tom Verguts
  
  CogSci | July 2023, Vol 45
  
  Publication
- Intrinsic rewards explain context-sensitive valuation in reinforcement learning
  
  Gaia Molinaro, Anne G. E. Collins
  
  PLOS Biology | July 2023, Vol 21(7): pp. e3002201
  
  Publication
- Human hacks and bugs in the recruitment of reward systems for goal achievement
  
  Gaia Molinaro, Anne G. E. Collins
  
  CogSci | July 2023, Vol 45
  
  Publication

Gaia Molinaro

Publications

Language model goal selection differs from humans’ in a self-driven learning task

Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science

Investigating the role of task representation switch costs in goal persistence

The Cultural Evolution of Human Goals

When 0 is good: instrumental learning with counterintuitive goals decreases working memory engagement

Spontaneous thought as play: the value of fictional goals in the default mode network

When LLMs play the telephone game: Cumulative changes and attractors in iterated cultural transmissions

ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models

Latent learning progress drives autonomous goal selection in human reinforcement learning

What should I do now? Goal-centric outlooks on learning, exploration, and communication

A goal-centric outlook on learning

Multifaceted information-seeking motives in children

A reinforcement learning framework for information-seeking and information-avoidance

Human hacks and bugs in the recruitment of reward systems for goal achievement

Intrinsic rewards explain context-sensitive valuation in reinforcement learning

Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science

Investigating the role of task representation switch costs in goal persistence

The Cultural Evolution of Human Goals

When 0 is good: instrumental learning with counterintuitive goals decreases working memory engagement

Spontaneous thought as play: the value of fictional goals in the default mode network

Latent learning progress drives autonomous goal selection in human reinforcement learning

What should I do now? Goal-centric outlooks on learning, exploration, and communication

A goal-centric outlook on learning

Multifaceted information-seeking motives in children

A reinforcement learning framework for information-seeking and information-avoidance

Intrinsic rewards explain context-sensitive valuation in reinforcement learning

Human hacks and bugs in the recruitment of reward systems for goal achievement

Language model goal selection differs from humans’ in a self-driven learning task

Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science

When LLMs play the telephone game: Cumulative changes and attractors in iterated cultural transmissions

Latent learning progress drives autonomous goal selection in human reinforcement learning

ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models

Language model goal selection differs from humans’ in a self-driven learning task

ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models

Language model goal selection differs from humans’ in a self-driven learning task

Self-generated goals in the age of foundation models: artificial autotelic agents and their implications for cognitive science

Investigating the role of task representation switch costs in goal persistence

The Cultural Evolution of Human Goals

When 0 is good: instrumental learning with counterintuitive goals decreases working memory engagement

Spontaneous thought as play: the value of fictional goals in the default mode network

When LLMs play the telephone game: Cumulative changes and attractors in iterated cultural transmissions

Latent learning progress drives autonomous goal selection in human reinforcement learning

ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models

What should I do now? Goal-centric outlooks on learning, exploration, and communication

A goal-centric outlook on learning

Multifaceted information-seeking motives in children

A reinforcement learning framework for information-seeking and information-avoidance

Intrinsic rewards explain context-sensitive valuation in reinforcement learning

Human hacks and bugs in the recruitment of reward systems for goal achievement