# SPECTRA-VLA：冻结 Vision-Language-Action 接口上的 Base-Fine 高光谱令牌迁移

> 原文链接：https://robotics.hellobike.com/papers/2026-10-14-2610-19651
> 频道：papers | 更新日期：2026-10-14 | 标签：arxiv, cs.RO
> 核心摘要：针对VLA冻结解码器难用高光谱状态的问题，SPECTRA-VLA以残差丰富目标令牌，并在86个留出采集上验证。

# SPECTRA-VLA：冻结 Vision-Language-Action 接口上的 Base-Fine 高光谱令牌迁移

::: v-pre
> 原文链接：[SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces](https://arxiv.org/abs/2610.19651)（arXiv 2610.19651 · 发布日期：2026-10-14）

**SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces**

针对VLA冻结解码器难用高光谱状态的问题，SPECTRA-VLA以残差丰富目标令牌，并在86个留出采集上验证。

## 核心要点

- 动机是高光谱可区分RGB相似物体，但预训练VLA需冻结解码器可用的状态。
- 方法在不重训视觉编码器或动作解码器下，用连续残差和伪彩参考丰富目标令牌。
- 通过投影、范数控制和验证校准注入调节变化，类别平衡准确率由0.812升至0.883。
- 同残差和尺度下，own-token addition在冻结解码器logits探针上优于pooled replacement。

**验证范围与局限**：验证范围限于86个留出采集及其分组测试，摘要未说明仿真或真机任务。

## 英文摘要 (Abstract)

Hyperspectral imaging distinguishes RGB-similar objects, but a pretrained vision-language-action model needs a state its frozen decoder can use. SPECTRA-VLA provides a native-width spectral upgrade without retraining the visual encoder or action decoder. A learned continuous residual enriches each target token through its own normalized false-color reference; projection, norm control and validation-calibrated injection regulate the change. Across 86 held-out acquisitions, category balanced accuracy rises from 0.812 to 0.883. With identical residuals and scale, own-token addition improves reuse of an external category-derived probe on frozen decoder logits: 0.701 versus 0.590 with pooled replacement, at similar image-disjoint recognition. Five grouped tests covering the same 86 acquisitions recover within-category spectral shape with $R^2=0.802/0.337$ from continuous and posterior-code states. Category-matched spectral swaps further show that own-token composition approximately doubles the target-specific recovery increment after frozen decoding. Spectral enrichment and receiving-token preservation thus work together at the pretrained interface.

作者：Chih-Chung Hsu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.19651：SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces](https://arxiv.org/abs/2610.19651)