SMILE: Smooth Motion for Improved Long-Horizon VLA Execution

2026-08-29

AI Summary

为解决长时序下VLA模型精度下降问题，提出SMILE方法，通过预测B样条系数生成平滑动作序列，提高执行效率和准确性。

Abstract

Vision-Language-Action (VLA) models reduce inference cost by executing multiple actions per call, but longer horizons often degrade accuracy because raw chunks contain jitter and outliers. We introduce SMILE, an architecture-preserving interface that predicts B-spline coefficients and decodes them into smooth action sequences. SMILE changes only the action representation, enabling longer fixed horizons while retaining each baseline's backbone and model scale. We apply SMILE to SmolVLA, Evo1, VPP, and DAWN, improving accuracy and amortized inference efficiency across LIBERO, CALVIN, and real-world experiments. SMILE-Evo1 reaches 98.0% with a 1.1x speedup on LIBERO, while SMILE-VPP reaches an average length of 4.42 with a 1.5x speedup on CALVIN. At a matched execution horizon of 10, SMILE-SmolVLA reduces non-boundary acceleration by 78.6% and velocity sign-change rate by 42.3%. Real-world xArm tests show higher success, fewer drops, and fewer contacts. These results establish smooth coefficient-space generation as a route to accurate, efficient long-horizon VLA execution. Project page: jongwoopark7978.github.io/smilevla

Problem

• VLA
• long-horizon
• accuracy degradation
• jitter
• outliers

Innovation

• B-spline coefficients
• smooth action sequences
• long-horizon VLA execution
• inference efficiency