Continually Evolving Skill Knowledge in Vision Language Action Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yuxuan, Wang, Guangming, Yang, Zhiheng, Deng, Tianchen, Yao, Maoqing, Sheil, Brian, Wang, Hesheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911659849678848
author Wu, Yuxuan
Wang, Guangming
Yang, Zhiheng
Deng, Tianchen
Yao, Maoqing
Sheil, Brian
Wang, Hesheng
author_facet Wu, Yuxuan
Wang, Guangming
Yang, Zhiheng
Deng, Tianchen
Yao, Maoqing
Sheil, Brian
Wang, Hesheng
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2511_18085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continually Evolving Skill Knowledge in Vision Language Action Model
Wu, Yuxuan
Wang, Guangming
Yang, Zhiheng
Deng, Tianchen
Yao, Maoqing
Sheil, Brian
Wang, Hesheng
Robotics
Artificial Intelligence
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/
title Continually Evolving Skill Knowledge in Vision Language Action Model
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2511.18085