PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models

TL;DR

PriorVLA introduces a method that preserves pretrained priors while adapting vision-language-action models for robot tasks, achieving better performance especially in out-of-distribution and few-shot scenarios.

Contribution

It proposes a novel framework that keeps a frozen prior source and trains a small adaptation module, improving adaptation efficiency and effectiveness over full fine-tuning.

Findings

PriorVLA outperforms full fine-tuning and state-of-the-art baselines.

Achieves 99.1% success on LIBERO benchmark.

Significant gains in out-of-distribution and few-shot settings.

Abstract

Large-scale pretraining has made Vision-Language-Action (VLA) models promising foundations for generalist robot manipulation, yet adapting them to downstream tasks remains necessary. However, the common practice of full fine-tuning treats pretraining as initialization and can shift broad priors toward narrow training-distribution patterns. We propose PriorVLA, a novel framework that preserves pretrained priors and learns to leverage them for effective adaptation. PriorVLA keeps a frozen Prior Expert as a read-only prior source and trains an Adaptation Expert for downstream specialization. Expert Queries capture scene priors from the pretrained VLM and motor priors from the Prior Expert, integrating both into the Adaptation Expert to guide adaptation. Together, PriorVLA updates only 25% of the parameters updated by full fine-tuning. Across RoboTwin 2.0, LIBERO, and real-world tasks, PriorVLA achieves stronger overall performance than full fine-tuning and state-of-the-art VLA baselines, with the largest gains under out-of-distribution (OOD) and few-shot settings. PriorVLA improves over pi0.5 by 11 points on RoboTwin 2.0-Hard and achieves 99.1% average success on LIBERO. Across eight real-world tasks and two embodiments, PriorVLA reaches 81% in-distribution (ID) and 57% OOD success with standard data. With only 10 demonstrations per task, PriorVLA reaches 48% ID and 32% OOD success, surpassing pi0.5 by 24 and 22 points, respectively.