ビジョン・言語・アクションモデルにおける継続的に進化するスキル知識
原題: Continually Evolving Skill Knowledge in Vision Language Action Model
分析結果
- カテゴリ
- 教育
- 重要度
- 59
- トレンドスコア
- 18
- 要約
- 本記事では、ビジョン・言語・アクションモデルにおけるスキル知識の進化について探求します。特に、モデルがどのようにして新しい情報を取り入れ、適応し、学習を続けるかに焦点を当てています。これにより、より効果的なタスク遂行が可能となり、AIの能力向上に寄与することが期待されます。
- キーワード
arXiv:2511.18085v3 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains challenging, especially for efficient adaptation. Existing continual imitation learning (CIL) methods often rely on additional parameters or external modules, limiting scalability for large VLA models. We propose Stellar VLA, a knowledge-driven CIL framework without increasing network parameters.Two progressively extended variants are designed: T-Stellar for flat task-centric modeling and TS-Stellar for hierarchical task-skill structure.Stellar VLA enables self-evolving knowledge learning by jointly optimizing task representations and a learned knowledge space. We propose a knowledge-guided expert routing mechanism conditioned on knowledge relation and Top-K semantic embeddings, enabling task specialization without increasing model size. Experiments on the LIBERO benchmark show that Stellar VLAs achieve strong performance among both VLA and CIL baselines, using only 1 % data replay. Real-world evaluation on a dual-arm platform with distinct embodiment and scene configurations validates effective knowledge transfer. TS-Stellar excels in hierarchical manipulation, and visualizations reveal robust knowledge retention and task discovery.Project Website: https://stellarvla.github.io/ arXiv:2511.18085v3 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains challenging, especially for efficient adaptation. Existing continual imitation learning (CIL) methods often rely on additional parameters or external modules, limiting scalability for large VLA models. We propose Stellar VLA, a knowledge-driven CIL framework without increasing network parameters.Two progressively extended variants are designed: T-Stellar for flat task-centric modeling and TS-Stellar for hierarchical task-skill structure.Stellar VLA enables self-evolving knowledge learning by jointly optimizing task representations and a learned knowledge space. We propose a knowledge-guided expert routing mechanism conditioned on knowledge relation and Top-K semantic embeddings, enabling task specialization without increasing model size. Experiments on the LIBERO benchmark show that Stellar VLAs achieve strong performance among both VLA and CIL baselines, using only 1 % data replay. Real-world evaluation on a dual-arm platform with distinct embodiment and scene configurations validates effective knowledge transfer. TS-Stellar excels in hierarchical manipulation, and visualizations reveal robust knowledge retention and task discovery.Project Website: https://stellarvla.github.io/