外观
论文arXiv 2610.1965114 天前
SPECTRA-VLA：冻结 Vision-Language-Action 接口上的 Base-Fine 高光谱令牌迁移
原文链接：SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces（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
来源
本页事实对应的公开页面，以原文为准。