Skip to content
Preprint

Latent Cluster Analysis for Vision-Language-Action Models

Sep 2026 · 0 citations · 25 references
Computer Science

TL;DR

This work proposes LAVLA, a framework for latent cluster analysis of VLA models, and conducts a layer-wise study of the state-of-the-art GR00T N1.5 model, with particular focus on its action decoder.

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.

View source

Similar papers

Preprint Oct 2026

UniWAM: Unified World-Action Model

UniWAM is introduced, a unified architecture that integrates a physical reasoner, a world generator, and an action predictor to jointly learn semantic understanding of the physical world, visual generation, and action prediction and uncovers a log-linear scaling law of unified human-robot co-training.

Wen-Xuan Song, Jia-Yi Chen, Jing-Bo Wang et al. · 6 citations · ⚡2
#artificial intelligence Preprint Sep 2026

The Linear Representation Hypothesis for Vision-Language-Action Models

A theoretical, signature-based formulation of the LRH for VLA that unifies representations and policies is developed, and a signature generalized linear model for stochastic action chunks is introduced for stochastic action chunks.

Min-hye Jeong, Hyewon Choi, Hiroyasu Tsukamoto et al. · 0 citations
Preprint Oct 2026

Juno: Taming Predictive Latents for Vision-Language-Action Models

Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predictive latents for vision-language-action (VLA) models. Yet making these latents useful across pretraining, policy learning, and deployment requires addressing three failures:...

Yu-Chen Zhu, Chen-Yi Xu, Yu-Lin Zhang et al. · 0 citations
Preprint Aug 2026

Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

Intention Distillation (INDI) is proposed, which distills behavior-level intent into the action decoder and organizes downstream predictions in an objective-dependent manner, and shows that action decoders benefit from explicitly modeling the semantic objective of the behavior they generate.

Sangoh Lee, Sang-Woo Mo, Wook-Shin Han · 1 citation
#machine learning Preprint Sep 2026

Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead

Vision-Language-Action (VLA) models remain brittle under visual distribution shifts, often relying on spurious correlations tied to domain-specific factors rather than task-relevant structure. We propose Domain-Invariant Latent Lookahead (DILL), a representation-learning framework that mitigates shortcut learning in VL...

Junghyun Kim, Ngseo Kim, Chung-Woo Lee et al. · 0 citations
Preprint Oct 2026

PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies

Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future representation is modeled and how it conditions action generation. We introduce PLaW-VLA, which models task-relevant future states in...

Yu Liu, He-Tian Guo, Tianlv Huang et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.