重新思考VLA初始化中的VLM表徵

摘要

视觉-语言-动作模型（VLA）广泛采用预训练的视觉-语言模型（VLM）作为策略主干，但何种预训练VLM表征有利于作为VLA初始化仍不明确。本文从三个维度研究VLA初始化这一可控表征设计问题：能力层面的具身VQA监督、参数更新策略以及机器人数据预训练。实验表明，原始预训练VLM表征是动作性能的关键来源。然而，具身VQA适应并未带来一致增益：其效益取决于下游瓶颈，且不同能力领域的增益并非简单相加。在更新策略方面，LoRA比全量微调提供了更可靠的初始化，表明过度重塑预训练表征会削弱VLA初始化效果。机器人数据预训练可进一步改善VLA初始化，其中基于LoRA的分阶段训练实现了最强变体。综合来看，这些发现表明：有效的VLM到VLA适配应在注入与动作相关的具身和机器人轨迹信号的同时，保留对动作学习有用的预训练VLM表征。

English

Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is useful as a VLA initialization. In this paper, we study VLA initialization as a controlled representation-design problem along three axes: capability-level embodied VQA supervision, parameter-update strategy, and robot-data pretraining. Our experiments show that the original pretrained VLM representation is a key source of action performance. However, embodied VQA adaptation does not yield uniform gains: its benefit depends on downstream bottlenecks, and gains from different capability domains are not simply additive. For update strategy, LoRA provides a more reliable initialization than Full Finetune, indicating that overly reshaping the pretrained representation can weaken VLA initialization. Robot-data pretraining further improves VLA initialization, with the strongest variant obtained by staged LoRA-based training. Together, these findings suggest that effective VLM-to-VLA adaptation should inject action-relevant embodied and robot-trajectory signals while preserving the pretrained VLM representation that remains useful for action learning.