Continually Evolving Skill Knowledge in Vision Language Action Model

arXiv:2511.18085 · cs.RO, cs.AI · Submitted 2025-11-22 · Read on arXiv

cs.RO, cs.AI

Submitted: 2025-11-22

Updated: 2026-10-18

Project page: https://stellarvla.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• VLA Models — 1× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 5 episodes

Sources

• TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
• On Tiny Episodic Memories in Continual Learning
• Behavior Generation with Latent Actions
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• OpenVLA: An Open-Source Vision-Language-Action Model
• AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
• Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
• CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
• Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
• Efficient Planning in a Compact Latent Action Space
• Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
• RT-H: Action Hierarchies Using Language
• What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models
• VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
• Auto-Encoding Variational Bayes
• Don't forget, there is more than forgetting: new metrics for Continual Learning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies