Latent Cluster Analysis for Vision-Language-Action Models

2026-09-02

AI Summary

为了解决VLA模型内部表示理解不足的问题，提出LAVLA框架进行潜在聚类分析，并引入基于交叉注意力的嵌入加权方法以优化特征表达。

Abstract

Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving their behaviour remain poorly understood. We propose LAVLA, a framework for latent cluster analysis of VLA models, and conduct a layer-wise study of the state-of-the-art GR00T N1.5 model, with particular focus on its action decoder. To better characterise the latent space during action diffusion, we introduce a cross-attention-based embedding-weighting method that amplifies relevant features while suppressing less informative ones. Quantitative evaluation shows that weighted clustering consistently outperforms the baseline. To improve interpretability, we extract human-interpretable concepts for each cluster, linking latent representations to semantic descriptions. Our analysis shows that latent clusters progressively disentangle spatiotemporal and kinematic features, with representations becoming more refined in the middle layers and stabilising toward the output. As such, LAVLA advances the interpretability of language-driven robotic systems.

Problem

• Vision-Language-Action Models
• latent cluster analysis
• internal representations

Innovation

• Latent Cluster Analysis
• Cross-Attention-Based Embedding-Weighting
• Interpretability
• VLA Models