Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

原文：Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

作者：Yunfei Xie, Howard H. Qian, Shiyi Lan, Kaiyu Hang, Chen Wei

来源：arXiv cs.LG（机器学习）

正文

Computer Science > Computer Vision and Pattern Recognition

arXiv:2610.31670v1 (cs)

[Submitted on 22 Oct 2026]

Title:Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Authors:Yunfei Xie, Howard H. Qian, Shiyi Lan, Kaiyu Hang, Chen Wei

View a PDF of the paper titled Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success, by Yunfei Xie and 4 other authors

View PDF

HTML (experimental)

Abstract:Robotic foundation models are typically evaluated through costly closed-loop rollouts, which motivates cheap offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, different 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 examine 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 across embodied model families, making it a low-cost offline proxy for prioritizing models before closed-loop evaluation. $S^2$ can also identify promising vision-language model (VLM) backbones even before costly fine-tuning into vision-language-action models (VLAs). Beyond this correlation, $S^2$ offers representation-level explanations for phenomena observed in VLAs and world action models (WAMs). With $S^2$, we extend PRH to embodied models and make sensorimotor alignment empirically measurable, offering insight into why an embodied model succeeds beyond its closed-loop success rate.

Comments:

28 pages. Project page and code available at this https URL

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO)

Cite as:

arXiv:2610.31670 [cs.CV]

(or

arXiv:2610.31670v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2610.31670

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

计算机视觉 · 机器学习 · 机器人

由「前沿雷达」于 2026-10-23 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。