Social-JEPA: Emergent Geometric Isomorphism
World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or coordination. After training, their internal representations exhibit a striking emergent property: the two latent spaces are related by an approximate linear isometry, enabling transparent translation between them. This geometric consensus survives large viewpoint shifts and scant overlap in raw pixels. Leveraging the learned alignment, a classifier trained on one agent can be ported to the other with no additional gradient steps, while distillation-like migration accelerates later learning and markedly reduces total compute. The findings reveal that predictive learning objectives impose strong regularities on representation geometry, suggesting a lightweight path to interoperability among decentralized vision systems. The code is available at https://anonymous.4open.science/r/Social-JEPA-5C57.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Decorrelation, Diversity, and Emergent Intelligence: The Isomorphism Between Social Insect Colonies and Ensemble Machine Learning
Social insect colonies and ensemble machine learning methods represent two of the most successful examples of decentralized information processing in nature and computation respectively. Here we develop a rigorous mathem…
Bayesian InferenceBehavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social information in dynamic scenes. For example, across a range of diverse vision mod…
GEOPHYS: The Geometry of Physical Plausibility
While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow and expensive. They either rely on external multimodal-LLM judges or…
Video GenerationMathematical representation of the structure of neuron-glia networks
Network representations of the nervous system have been useful for the understanding of brain phenomena such as perception, motor coordination, and memory. Although brains are composed of both neurons and glial cells, ne…
Koopman Invariants as Drivers of Emergent Time-Series Clustering in Joint-Embedding Predictive Architectures
Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretic…
Self-Supervised Learning