Dense to MoE Adaptation for Compact Vision Language Action Policies

2026-09-14

AI Summary

为减少视觉语言动作策略在资源受限机器人平台上的参数，提出AdaDE方法，将密集前馈块转换为混合专家层，并通过动态更新专家掩码来保持性能。

Abstract

Vision language action (VLA) policies continue to grow in parameter count, making deployment on resource-constrained robot platforms difficult. The central goal is to reduce the number of LLM-side parameters retained in the deployed policy while preserving downstream task performance. Our approach, AdaDE, adapts selected dense feed forward blocks into mixture of experts (MoE) layers and derives expert retention masks from router statistics during fine tuning. The Dense2MoE conversion preserves the original dense FFN function at initialization, so expert deactivation can start without a separate recovery stage. Instead of using a fixed shutdown rule, expert masks are updated dynamically from router usage statistics, with staged training and expert protection to avoid early collapse. With 40% of the LLM parameters deactivated, AdaDE retains 95.1% average success in LIBERO and 42.0% average success across all 50 RobotWin2.0 tasks. These results suggest that dense to MoE adaptation with dynamic expert deactivation is a practical direction for reducing active VLA model size without severe performance loss.

Problem

• Vision Language Action
• Parameter Reduction
• Resource-Constrained Platforms
• Downstream Task Performance

Innovation

• Dense2MoE
• dynamic expert deactivation
• router statistics
• staged training
• expert protection