Filter across the whole symbol-emergence hub. Searches titles, authors, tags, and summaries.
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.
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.
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.
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.
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.
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.
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.
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.
PI: (Multiple PIs)
Multi-agent learning and emergent communication research at DeepMind, spanning cooperation, competition, language emergence, and societal-scale simulations of intelligent agents.
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.
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.
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.
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.
Sep 12, 2026 – Sep 14, 2026 · Kyoto, Japan
Annual symposium on symbol emergence systems, covering theoretical and applied research in cognitive robotics. Tracks include MHNG, multimodal concept formation, embodied language acquisition, and multi-agent communication.
Jul 1, 2026 – Jul 29, 2026 · Online
A four-week online reading group covering recent CPC and active inference papers. Sessions alternate between English and Japanese facilitation; reading materials are bilingual where possible.
Jun 15, 2026 – Jun 17, 2026 · London, UK
Three-day workshop on the latest theoretical and applied developments in active inference and the free-energy principle. Mixed-format programme with invited talks, posters, and small-group tutorials.
Dec 12, 2025 · San Diego, USA
The annual NeurIPS workshop on emergent communication, bringing together research on multi-agent reinforcement learning, language emergence, and the relationship between emergent and natural languages.
Jul 23, 2025 – Jul 26, 2025 · San Francisco, USA
The 47th annual meeting of the Cognitive Science Society. Sessions include symbol grounding, computational modelling of cognition, and language emergence in humans and machines.
アテンション・エコノミー時代のいま、そして、これからの科学コミュニケーションはどうあるべきか、メタサイエンス ...
Watch on YouTube →
「予測誤差を食らう」とは何なのか、『行為する意識』の著者のひとりである吉田さんに直撃インタビューました！ 0:00 スタート ...
科学は現代科学と協働できるのか、進化生物学者が哲学者の平井さんに対談バトルを挑みました！ 【チャプター】 00:00 ...
ロボットは感情をもてるのか、進化生物学者がロボット工学者の堀井さんに対談バトルを挑みました！ 【チャプター】 00:00 ...
科学者の仕事、科学という営みの目的と本質、そして科学におけるAI利用について、藤井さんと語りました！ 【「集合的予測符号 ...
意味を理解しているとはどのようなことなのか、藤井さんと語りました！ 【「集合的予測符号化」シリーズ】 第1回 ...
生命の原理、飲みすぎやギャンブル中毒の背景にあるメカニズム、そして社会や言語の起源まで、藤井さんと語りました！ 【前回 ...
https://arxiv.org/pdf/2501.00226 LLMs as Decentralized Bayesian Inference of Collective World Models This paper introduces the ...
集合的予測符号化（Collective Predictive Coding, CPC）は、脳の予測符号化の原理を社会全体に拡張した理論です。複数の ...
こんにちは、記号創発アウトリーチチームです。本連載「記号創発スタディノート」は、京都大学の谷口忠大（通称：たにちゅー）教授を中心に10年以上にわたり展開されてきた「記号創発システム論」について、その可能性と意義、中心的な手法、今後の展望についてコンパクトに解説するシリーズです。◆これまでの回：・第1回：なぜ、いま記号創発システム論なのか？ ～生成AI時代の「意味」の新学理・第2回：記号創発システム論は何を問う？ ～記号接地問題から「記号
Read on note →
こんにちは、記号創発アウトリーチチームです。本連載「記号創発スタディノート」は、京都大学の谷口忠大（通称：たにちゅー）教授を中心に10年以上にわたり展開されてきた「記号創発システム論」について、その可能性と意義、中心的な手法、今後の展望についてコンパクトに解説するシリーズです。◆これまでの回：・第1回：なぜ、いま記号創発システム論なのか？ ～生成AI時代の「意味」の新学理へ・第2回：記号創発システム論は何を問う？ ～記号接地問題から「記
こんにちは、記号創発アウトリーチチームです。本本連載「記号創発スタディノート」は、京都大学の谷口忠大（通称：たにちゅー）教授を中心に10年以上にわたり展開されてきた「記号創発システム論」について、その可能性と意義、中心的な手法、今後の展望についてコンパクトに解説するシリーズです。
こんにちは、記号創発アウトリーチチームです。本連載記事「記号創発スタディノート」は、京都大学の谷口忠大（通称：たにちゅー）教授を中心に、過去10年以上にわたり展開されてきた「記号創発システム論」について、その可能性と意義、中心的な手法、今後の展望についてコンパクトに解説する連載シリーズです。
はじめまして、記号創発アウトリーチチームです。本連載記事「記号創発スタディノート」は、記号創発システム論の魅力と概要を知るための勉強ノートです。記号創発システム論は、京都大学の谷口忠大（通称：たにちゅー）教授を中心に、過去10年以上にわたり構想・展開されてきた学際的な分野。本連載では、その可能性と意義、中心的な手法、そして今後の展望についてコンパクトに解説し、多くの方がこの分野に入門し、言葉を共有して語り合える土台をつくれればと考えてい
