重新思考用于VLA初始化的VLM表示
Rethinking VLM Representation for VLA Initialization
AI总结：
本文通过控制表示设计问题，沿能力级具身VQA监督、参数更新策略和机器人数据预训练三个轴，研究VLA初始化，发现保留预训练VLM表示对动作性能至关重要，而LoRA比全微调提供更可靠的初始化，分阶段基于LoRA的训练获得最强变体。
摘要：
视觉-语言-动作（VLA）模型广泛采用预训练的视觉-语言模型（VLM）作为策略骨干，但目前尚不清楚何种预训练VLM表示对VLA初始化有用。在本文中，我们将VLA初始化作为一个受控的表示设计问题，沿三个轴进行研究：能力级具身VQA监督、参数更新策略和机器人数据预训练。我们的实验表明，原始预训练VLM表示是动作性能的关键来源。然而，具身VQA适应并不产生一致的收益：其收益取决于下游瓶颈，且来自不同能力域的收益并非简单相加。对于更新策略，LoRA提供了比全微调更可靠的初始化，表明过度重塑预训练表示会削弱VLA初始化。机器人数据预训练进一步改善了VLA初始化，通过分阶段基于LoRA的训练获得了最强变体。这些发现共同表明，有效的VLM到VLA适应应在保留对动作学习有用的预训练VLM表示的同时，注入与动作相关的具身和机器人轨迹信号。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
