Vision-Language-Action (VLA) models have emerged as the mainstream of embodied intelligence. Recent VLA models have expanded their input modalities from 2D-only to 2D+3D paradigms, forming multi-visual-modal VLA (MVLA) models. Despite achieving improved spatial perception, MVLA faces a greater acceleration demand due to the increased number of input tokens caused by modal expansion. Token pruning is an effective optimization methods tailored to MVLA models. However, existing token pruning schemes are designed for 2D-only VLA models, ignoring 2D/3D modality salience differences. In this paper, we follow the application process of multi-modal data in MVLA models and develop a tri-stage analysis to capture the discrepancy and dynamics of 2D/3D modality salience. Based on these, we propose a corresponding tri-stage token pruning framework for MVLA models to achieve optimal 2D/3D token selection and efficient pruning. Experiments show that our framework achieves up to a 2.55x inference speedup with minimal accuracy loss, while only costing 5.8% overhead. Our Code is coming soon.

翻译：视觉-语言-动作（VLA）模型已成为具身智能的主流范式。近期VLA模型将输入模态从仅2D扩展到2D+3D范式，形成多视觉模态VLA（MVLA）模型。尽管空间感知能力得到提升，但模态扩展导致的输入词元数量增加使MVLA面临更大的加速需求。词元剪枝是针对MVLA模型的有效优化手段。然而现有剪枝方案仅针对纯2D VLA模型设计，忽视了2D/3D模态显著性的差异。本文遵循多模态数据在MVLA模型中的处理流程，通过三阶段分析揭示2D/3D模态显著性的差异性与动态变化规律。基于此，我们提出面向MVLA模型的对应三阶段词元剪枝框架，实现最优的2D/3D词元选择与高效剪枝。实验表明，本框架在仅增加5.8%额外开销的情况下，实现了最高2.55倍推理加速且精度损失极小。代码即将发布。