In 1950, Alan Turing asked "Instead of trying to produce a programme to simulate the adult mind, why not rather try to produce one which simulates the child's?" Today, 75 years later, constructing a computer program that can learn like a child and that develops a human-like general intelligence and consciousness is still considered a grand, if not the ultimate, challenge for artificial intelligence (AI). An interdisciplinary community of scientists from AI, Cognitive Science, Psychology, Engineering, and Neuroscience are tackling this grand challenge. In the Developing Minds global lecture series we showcase the progress being made. It is organized by the Developmental AI Task Force of the IEEE Technical Committee on Cognitive and Developmental Systems of the IEEE Computational Intelligence Society. See also: IEEE Int. Conference on Development and Learning (ICDL), IEEE Transactions on Cognitive and Developmental Systems (TCDS). If you enjoy this lecture series, you may also enjoy the keynote lectures and all oral presentations from the last ICDL conference.

Next Event

Thursday, October 1, 2026

08:00 am EDT (Eastern Daylight Time, USA)

 12:00 UTC (Universal Coordinated Time)

 14:00 CEST (Central European Summer Time)

 21:00 JST  (Japan Standard Time)

https://uni-frankfurt.zoom-x.de/j/69685146703?pwd=fUXECYbxVOBjuH9dzg02vO1PFOwVSS.1

Meeting-ID: 696 8514 6703

Code: 116482

Jun Tani

Okinawa Institute of Science and Technology (OIST)

"From Embodied Language Grounding to Systematic Generalization: Developmental Origins of Compositionality in Robots"

Abstract

How can infants develop skills for action and language from relatively limited experience through interaction with the world? This seminar presents a developmental robotics perspective on this question by investigating how compositionality—the capacity to systematically recombine known concepts in novel situations—can emerge through embodied interaction. First, we introduce a brain-inspired neural model based on predictive coding, active inference, and the free-energy principle, in which language, vision, and action are learned jointly [1]. Robotic experiments demonstrate that compositional linguistic representations emerge through sensorimotor experience, enabling generalization to previously unseen language-action combinations. Second, we discuss how self-exploration and intrinsic motivation can further support the development of systematic generalization under sparse learning conditions [2]. By integrating active inference with reinforcement learning, robots learn not only to achieve goals but also to seek information and behavioral novelty. The results suggest that richer compositional experiences promote the emergence of structured internal representations that support generalization beyond training examples. Together, these studies suggest that compositional intelligence can emerge from embodied predictive learning and active exploration, offering a possible developmental account of how systematic generalization can arise from relatively limited experience.

[1] Vijayaraghavan, P., Queißer, J. F., Verduzco-Flores, S., & Tani, J. “Development of compositionality through interactive learning of language and action of robots.” Science Robotics, 10, eadp0751, 2025.

[2] Tinker, T. J., Doya, K., & Tani, J. “Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration.” Science Advances, 12, eaee7533.

Short Bio

Jun Tani received the D.Eng. degree from Sophia University, Tokyo in 1995. He started his research career with Sony Computer Science Lab. in 1993. He became a PI in RIKEN Brain Science Institute in 2001. He became a tenured Professor at KAIST, South Korea in 2012. He is currently a full Professor at OIST. He is also a visiting professor at The Technical University of Munich. His current research interests include cognitive neuroscience, developmental psychology, phenomenology, complex adaptive systems, and robotics. He is an author of “Exploring Robotic Minds: Actions, Symbols, and Consciousness as Self-Organizing Dynamic Phenomena." published from Oxford Univ. Press in 2016.

Please sign up here to receive access information and announcements of future talks.

Upcoming Events

• 2026-10-01: Jun Tani, Okinawa Institute of Science and Technology (OIST), Japan

• 2026-10-15: Michael H. Goldstein, Cornell Univ., USA

Previous Events

• 2026-06-25: Andrew Barto, "Rediscovering Reinforcement Learning". Video

• 2026-04-02: Lisa Oakes, "Learning to look and looking to learn: Developmental cascades in infant attention". Video

• 2025-12-04: Jenny Saffran, "Learning to understand: Statistical learning and language development". Video

• 2025-11-13: Tadahiro Taniguchi, "Developing Collective Minds: Symbol Emergence and Co-creative Learning via Collective Predictive Coding". Video

• 2025-10-16: Denis Mareschal, "The challenges and rewards of pursuing real-world Developmental Science". Video

• 2025-09-25: Uri Hasson,  "Developing cognitively feasible learning agents that can acquire language like children through real-life experiences". Video not yet available.

• 2024-12-12: Daniel Messinger, "Does Interaction Drive Development? Lessons from infant emotion, autism, and preschool language". Video

• 2024-11-12: Justin N. Wood, "Radical empiricism: The origins of knowledge as a mini-evolution". Video

• 2024-04-18: Sabine Hunnius, "Early cognitive development: Five lessons from infant learning". Video

• 2024-01-24: Caroline Rowland, "What predicts how quickly children learn language?" Video

• 2023-11-30: Brenden Lake, "Addressing two classic debates in cognitive science with deep learning". Video

• 2023-06-28: Angelo Cangelosi, "Developmental Robotics for Language Learning, Trust and Theory of Mind". Video

• 2023-04-27: Karl Friston, "Active Inference and Artificial Curiosity". Video

• 2023-03-02: Masashi Sugiyama, "Theory and Algorithm towards Reliable Machine Learning". Video

• 2022-12-08: Karen E. Adolph, "Development of intelligent behavior: Lessons from Infants". Video

• 2022-11-17: Gary Marcus, "Towards a Proper Foundation for Robust Artificial Intelligence". Video

• 2022-07-28: Sergey Levine, UC Berkeley, "From Reinforcement Learning to Embodied Learning". Video

• 2022-06-01: Susan Goldin-Meadow, U. of Chicago, "The Mind Hidden in Our Hands". Video

• 2022-03-31 : Atsushi Iriki, Riken, "Self-in-the-world map evolved in the primate brain as a basis of civilized Homo sapiens". Video

• 2022-01-27: Josh Tenenbaum, MIT, "Reverse Engineering Human Cognitive Development: What do we start with, and how do we learn the rest?". Video

• 2021-11-11: Linda B. Smith, Indiana University, "Babies, bodies, brains and machines". Video  

• 2021-09-30: Pierre-Yves Oudeyer, INRIA, "Developmental Artificial Intelligence: machines that learn like children and help children learn better".  Video

Initiators