先丢弃后恢复：视觉-语言-动作模型的冗余性有多高？

摘要

视觉-语言-动作（VLA）模型实现了指令驱动的机器人操控，但它们继承了预训练VLM中庞大的语言主干网络，其容量远超简短机器人指令所需。这引出一个基本问题：VLA模型中有多少部分对闭环控制是真正必要的？在本研究中，我们通过将Transformer模块移除作为受控干预手段，探讨VLA模型中的架构冗余性。我们提出"丢弃-恢复"协议（DTR），该分析流程从预训练VLA模型中移除选定模块，随后对所得模型进行微调，以衡量被移除容量对下游控制是否必要。为提升该干预的可靠性，我们提出GateProbe——一种一次性虚拟门控敏感度指标，用于按模块对下游动作损失贡献度进行排序。在多种VLA架构、操控基准测试乃至真实机器人工厂场景中，我们发现在移除后恢复能力存在显著不对称性：语言主干网络对标准机器人操控任务高度冗余，而视觉和动作路径对移除的容忍度则显著较低。在LIBERO数据集上，移除半数大语言模型模块后，在相同下游微调预算下甚至将OpenVLA-OFT性能从95.0%提升至98.3%，且仅保留两个语言模块仍能恢复基线性能。这些结果表明，当前VLA基准测试可能对深度语言基础与组合指令理解施加的压力有限，未来VLA架构应在语言、视觉与动作组件之间更审慎地分配容量。代码已开源：https://github.com/s1ghhh/VLADrop。

English

Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds what is needed for short robotic instructions. This raises a basic question: how much of a VLA model is actually necessary for closed-loop control? In this work, we study architectural redundancy in VLA models by using transformer block removal as a controlled intervention. We introduce Drop-Then-Recovery (DTR), an analysis protocol that removes selected blocks from a pretrained VLA model and then fine-tunes the resulting model to measure whether the removed capacity was necessary for downstream control. To make this intervention reliable, we propose GateProbe, a one-shot virtual-gate sensitivity metric that ranks blocks by their contribution to the downstream action loss. Across multiple VLA architectures, manipulation benchmarks and even real-robot industrial scenarios, we find a strong asymmetry in post-removal recoverability: \textit{language backbones are highly redundant for standard robotic manipulation tasks, whereas vision and action pathways are substantially less tolerant to removal}. On LIBERO, removing half of the LLM blocks even improves OpenVLA-OFT from 95.0% to 98.3% under the same downstream fine-tuning budget, and retaining only two language blocks still recovers baseline-level performance. These results suggest that current VLA benchmarks may exert limited pressure on deep language grounding and compositional instruction understanding, and that future VLA architectures should allocate capacity more deliberately across language, vision, and action components. The code is available at https://github.com/s1ghhh/VLADrop.