LATIDIA · Robótica

Alineación sensoriomotora: un proxy platónico para el éxito de la política incorporada

arXiv: 2610.31670v2 Announce Type: replace-cross Abstract: Los modelos de cimentación de robots generalmente se evalúan a través de costosos despliegues de bucle cerrado, lo que motiva a los proxies fuera de línea de bajo costo para la capacidad del modelo. Platonic Repres

La noticia

arXiv:2610.31670v2 Announce Type: replace-cross Abstract: Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, modalities such as vision and language converge toward a shared statistical model of reality. We ask whether motion trajectories form another such modality: as embodied models become more capable, should their sensory representations converge toward the structure of physical motion? To test this, we propose Sensorimotor Alignment ($S^2$), a training-free offline metric that measures how well a model's sensory representation aligns with the geometry of physical motion. We find that $S^2$ correlates positively with downstream robot task success