Papers
Systematic curation of CPC-related research papers.
Synchronizing Minds through Collective Predictive Coding: A Computational Model of Parent-Infant Homeostatic Co-Regulation
Yushi Tsubamoto, Takato Horii
Inter-brain synchrony (IBS) observed in real-time dyadic interactions, including parent--infant exchanges, suggests that two agents come to share aligned latent representations through interaction. Yet computational accounts of how such alignment can arise between agents that have only local sensory access and asymmetric internal knowledge remain underdeveloped. We propose a constructive model of parent--infant homeostatic co-regulation that integrates a POMDP formulation of active interoceptive inference with the Metropolis--Hastings Naming Game (MHNG) derived from the Collective Predictive Coding (CPC) hypothesis. In our model, the parent observes the infant only through an exteroceptive signal while the infant directly senses its own interoceptive state; the two agents agree on regulatory actions through a shared communicative variable whose acceptance is determined by a locally computable Metropolis--Hastings probability. The agents are further endowed with asymmetric generative-model knowledge: the parent knows how actions transform visceral states but must learn what the infant's body is communicating, whereas the infant perceives its visceral state directly but must learn how actions affect it. In a $6 \times 6$ visceral-state grid world, MHNG-mediated interaction regulated the infant's visceral state more adaptively than one-sided control conditions, and the two posteriors became rapidly aligned. Notably, this latent-state alignment emerged far earlier than the convergence of the learned generative matrices, indicating that representational synchrony does not presuppose fully shared world models. These results offer a minimal constructive account of latent-state alignment compatible with IBS reported in hyperscanning studies and support CPC as a candidate computational basis for inter-brain alignment.
Emergence of Social Reality of Emotion through a Social Allostasis Model with Dynamic Interpretants
Kentaro Nomura, Yushi Tsubamoto, Takato Horii
The theory of constructed emotion defines social reality as the community-level consensus on emotion concepts assigned to interoceptive sensations arising from bodily allostasis and social interaction. In this study, we simulate this emergence process using a computational model that integrates symbol emergence with degrees of freedom in symbol interpretation and active inference. Two agents receive interoceptive signals, exchange inferred symbols, and simultaneously adapt their bodily control goals and symbol interpretations to each other. Experimental results show that the interoceptive prior preferences and symbol probability distributions of the two agents converge, confirming the emergence of social reality grounded in social consensus.
Emergent Communication for Co-constructed Emotion Between Embodied Agents via Collective Predictive Coding
Zehang Zhang, Nguyen Le Hoang, Tadahiro Taniguchi, et al.
According to the theory of constructed emotion, the brain actively forms emotion categories by integrating multimodal bodily signals, and constructs emotional experiences by using these categories to predict and interpret sensory inputs. While research has advanced in modeling individual emotion construction, the social process of co-construction-how a shared understanding of emotions emerges between individuals-remains computationally underexplored. This study investigates this process by modeling emergent communication between two embodied agents using the Metropolis-Hastings Naming Game (MHNG), grounded in the Collective Predictive Coding (CPC) framework. Our experiments, using visual, auditory, and simulated interoceptive inputs, yield two main findings. First, MHNG-based communication significantly improves the alignment, clarity, and inter-agent agreement of the learned emotion categories compared to non-communicative and non-selective baselines, with the alignment effect concentrated at the symbolic layer rather than the perceptual latent representation. Second, even when the two agents have systematically divergent interoceptive dynamics, communication still produces robust categorical alignment, with distinct, category-specific reshaping patterns of each agent's emotion categories-consistent with the constructed-emotion view that interoceptive heterogeneity is constitutive of, rather than an obstacle to, shared emotional meaning. These findings provide computational support for the co-constructionist view of emotion and extend the CPC framework from physical to socially-grounded domains.
Decentralized Collective World Model for Emergent Communication
Ebara, T., Inoue, R., Taniguchi, T.
We propose a collective world model in which multiple agents share a common generative latent space through emergent communication. Decentralized inference on this shared space yields stable cooperative behavior without a central controller, suggesting a path from world models to compositional symbols.
Collective Predictive Coding Hypothesis: Symbol Emergence as Decentralized Bayesian Inference
Taniguchi, T., Yoshida, M., Matsui, Y., et al.
Understanding the emergence of symbol systems, especially language, requires a computational model that reproduces both the developmental learning process in everyday life and the evolutionary dynamics of symbol emergence throughout history. This paper proposes the Collective Predictive Coding (CPC) hypothesis, framing symbol emergence as decentralized Bayesian inference performed jointly by interacting agents.
Metropolis-Hastings Naming Game: Symbol Emergence as Probabilistic Generative Models
Hagiwara, Y., Kobayashi, H., Taniguchi, A., et al.
We propose the Metropolis-Hastings Naming Game (MHNG), a probabilistic generative model that derives the dynamics of symbol emergence as Bayesian inference. Acceptance and rejection of partner messages are formalised as Metropolis-Hastings steps, providing a principled bridge between multi-agent communication and posterior sampling.
Active Inference: A Process Theory
Friston, K., FitzGerald, T., Rigoli, F., et al.
This article presents active inference as a unifying process theory for perception, action, and learning under the free-energy principle. Behaviour is cast as inference over policies that minimise expected free energy, combining epistemic (information-seeking) and pragmatic (goal-directed) drives in a single objective.
Emergent Communication in Multi-Agent Reinforcement Learning: A Survey
Lazaridou, A., Baroni, M.
We survey approaches to emergent communication in multi-agent reinforcement learning, organising them around the dimensions of language input, learning signal, and population structure. We argue that scaling toward human-language-like systems requires bridging emergent and natural-language research traditions.