Towards Efficient Embodied Reasoning: Mixture-of-Depth Compute Allocation for Vision-Language-Action Model
TL;DR
MoDeVLA is proposed, the first rate-distortion driven efficient VLA model that performs token-wise depth allocation via Mixture-of-Depth Conditioning and integrates shallow visual-spatial with deep textual-logical features for action conditioning and introduces Effective-Edge Flow, an action-aligned attribution measure that quantifies the marginal contribution of token interactions across network depth.
Abstract
Vision-Language-Action (VLA) model plays a crucial role in embodied decision making. While practical deployment requires fast inference under limited onboard computation, a full forward pass through the vision-language model makes such deployment challenging. To address this issue, existing methods typically employ lightweight techniques to compress the backbone. However, these information-lossy methods degrade spatial representations for action generation. In contrast, rate-distortion principles aim to reduce computation while retaining control-sufficient information. Inspired by this insight, we introduce Effective-Edge Flow, an action-aligned attribution measure that quantifies the marginal contribution of token interactions across network depth. This analysis reveals a consistent depth asymmetry, with visual evidence dominating early layers and linguistic reasoning sustaining task-relevant influence into deeper layers. Building on this structure, we propose MoDeVLA, the first rate-distortion driven efficient VLA model that performs token-wise depth allocation via Mixture-of-Depth Conditioning and integrates shallow visual-spatial with deep textual-logical features for action conditioning. Extensive real-robot evaluations across 20 tasks and multiple embodiments demonstrate that MoDeVLA preserves task performance while reducing latency by about 38% and FLOPs by 86% on edge device NVIDIA Jetson Orin, highlighting its strong ability for embodied systems deployment.