symbol-emergence hub

Labs

Research groups working on symbol emergence and collective predictive coding.

Google DeepMind · United Kingdom

Google DeepMind — Multi-Agent Research

PI: (Multiple PIs)

Multi-agent learning and emergent communication research at DeepMind, spanning cooperation, competition, language emergence, and societal-scale simulations of intelligent agents.

Multi-agent Emergent Communication Reinforcement Learning
University College London · United Kingdom

Theoretical Neurobiology Group (Friston Lab)

PI: Karl Friston

The Wellcome Trust Centre for Human Neuroimaging hosts the theoretical neurobiology group, which develops the free-energy principle and active inference as a unifying account of perception, action, and learning.

Active Inference Predictive Coding Free Energy Principle
New York University · United States

Human & Machine Learning Lab

PI: Brenden Lake

The lab develops computational models of how humans learn rich, structured concepts from limited experience, and how machines can do the same. Recent work has focused on systematic generalisation in neural networks.

Symbol Emergence Compositionality Cognitive Modeling
MIT CSAIL · United States

Improbable AI Lab

PI: Pulkit Agrawal

Research at the intersection of robot learning, multi-agent systems, and emergent behaviour. The lab studies how communication, coordination, and generalisation arise in embodied agents trained at scale.

Multi-agent Emergent Communication Robotics
Kyoto University / Ritsumeikan University · Japan

Taniguchi Lab — Symbol Emergence Systems

PI: Tadahiro Taniguchi

Research focused on symbol emergence, multimodal robotics, and the Collective Predictive Coding theory. The lab studies how concepts and language emerge from sensorimotor experience in artificial and biological agents.

Symbol Emergence CPC Multimodal Learning Robotics