視覚・言語・行動モデルの潜在クラスタ解析
Latent Cluster Analysis for Vision-Language-Action Models
VLAモデルの内部表現を層ごとに解析し、行動デコーダの潜在空間をクラスタリングして解釈可能な概念を抽出するフレームワークを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Theodor Wulff, Sergio Lanza, Tamara Bila, Angelo Cangelosi, Stefan Wermter, Igor Farkas
分類: cs.RO
原文アブストラクト
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.
関連論文
- VLA表現からのタスク進捗の解読VLA/解釈可能性
- VLA表現からのタスク進捗の解読VLA/解釈可能性