# B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations

arXiv: https://arxiv.org/abs/2607.09648 · HTML: https://mlsanity.com/paper/2607.09648/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2026.

## Built on by (most cited first, 5 of 5)

- [SMILE: Smooth Motion for Improved Long-Horizon VLA Execution](https://mlsanity.com/paper/2608.29432/) (2026)
- [LieSpline-DP: Lie-Group B-Spline Diffusion Policy for Smooth Robot Manipulation](https://mlsanity.com/paper/2609.15162/) (2026)
- [Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation](https://mlsanity.com/paper/2609.39822/) (2026)
- [SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations](https://mlsanity.com/paper/2609.39873/) (2026)
- [Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization](https://mlsanity.com/paper/2610.05230/) (2026)

## Abstract (arXiv)

In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks, BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points. This representation yields smooth, time-continuous trajectories that can be temporally scaled and executed by low-level controllers at higher frequencies and speeds. We show that B-spline-parameterized actions can be seamlessly integrated into standard policy learning pipelines by directly predicting B-spline parameters. Experiments on simulated and real-world tasks demonstrate that BSP significantly reduces task completion time, achieving substantial improvements over baseline methods while maintaining strong success rates. More results: https://b-spline-policy.github.io