【论文速递】From Pixels to Actions - Towards Native Vision-Language-Action Policies

英文标题：From Pixels to Actions - Towards Native Vision-Language-Action Policies

arXiv编号：2611.06918
作者：Weichen Fan, Haiwen Diao, Penghao Wu
来源：arXiv
原文链接：https://arxiv.org/abs/2611.06918

中文摘要：
Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals most vulnerable to this abstraction, e.g., local geometry, boundaries, depth, and subtle state changes. This raises a fundamental question: should action policies inherit a fixed visual endpoint, or directly access evolving visual computation? We introduce NEO-VLA, a structurally encoder-free vision-language-action framework. Images are tokenized by lightweight patch convolutional layers and evolve jointly with language throughout the backbone, allowing a flow-matching action expert to draw from instruction-conditioned visual representations at different depths. This simple change reveals a consistent pattern. Native architectures outperform encoder-based counterparts under controlled comparisons; full fine-tuning reduces but does not erase the gap, and additional scale alone cannot recover it. More strikingly, layer-wise probing shows that the action-critical signals often peak well before the final visual representation. Across diverse manipulation settings and distribution shifts, NEO-VLA consequently achieves stronger and more robust control. Together, these results suggest that embodied control benefits from access to visual representations across the computational hierarchy, rather than a fixed encoder output.

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。