28 min
Seminar, Hosted by Simons Institute for the Theory of Computing
Social NeuroAI of World Modeling: Embodied Dynamics, Collective Intelligence and Relational Computation
CR-CHUSJ / Mila - Quebec AI Institute, University of Montreal
Recording
Abstract
World models usually describe an individual agent's environment, but biological intelligence also depends on interaction with other agents. This talk brings together dynamical systems, inter-brain neuroscience and multi-agent modelling to study that relational setting. Embodied neural agents illustrate metastable coordination and collective decisions. The proposed direction for AI treats others as coupled systems with their own latent models, allowing shared representations and intelligence to emerge through interaction.
Topics
- world models
- biological intelligence
- inter-brain neuroscience, broader topic: neuroscience
- multi-agent modelling, search World Wide
- Embodied neural agents, broader topic: Agents
- metastable coordination, broader topic: coordination
- collective decisions, search World Wide
- coupled systems
- shared representations