← Back to all news
arXiv Machine Learning By Eduardo Righi Capanema de Almeida

A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding

Read the original on arXiv Machine Learning →

The paper introduces the Bayesian Mirror Architecture (BMA), a self-referential generative model where sensory abstractions, meta-abstractions, and a self-latent interact through a closed update loop, binding self-representations to abstract world models. Consciousness is defined as an architectural property of this circular structure rather than an optimization goal, with inference occurring over probability measures in an optimal-transport space. Stability, coherence, and causal learning are formalized using the 2‑Wasserstein metric, leading to concepts such as self-manifolds, Wasserstein epsilon-necks, and a Causal Learning Regime that diagnoses learnable causal structure without implying consciousness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 29

I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?

The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.

By Yuhang Liu, Zhuo Huang, Javen Qinfeng Shi
ragbenchmarks
More like this →
arXiv AI
Sep 10

We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consciousness

The paper argues that the current debate on machine consciousness rests on the mistaken assumption that AI systems are already the kind of entities that could possess consciousness. By distinguishing between phenomenal consciousness, introspective report, and human projective introspection, it introduces the AI Consciousness Fallacy, showing that generative models can produce first‑person linguistic traces without being conscious. It then proposes Causal Liability Theory (CLT), with CLT‑I defining liability closure as a criterion for identifying a bearer of consciousness and CLT‑II suggesting that liability closure is both necessary and sufficient for minimal phenomenal subjecthood, and demonstrates experimentally that these distinctions are tractable and can separate causal bearer structure from first‑person performance.

By Afshin Khadangi
More like this →
arXiv AI
Oct 1

From cacophony to hierarchy: a principled framework for assessing AI consciousness

arXiv:2609.35618v2 Announce Type: replace Abstract: The question of AI consciousness is one of the most urgent pre-emptive problems in philosophy and computer science, yet progress is hampered by a c...

By Shamil Chandaria, Arvo Mu\~noz Mor\'an, Fernando Rosas, Anil Seth, Henry Shevlin, Marcus Hutter, Thore Graepel, Adam Bales, Iulia Comsa, Murray Shanahan, Ruben Laukkonen, Morten Kringelbach, Chris Frith, Shane Legg
llms
More like this →