# Frequency-Conditioned Flow Matching for Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2609.10405 · HTML: https://mlsanity.com/paper/2609.10405/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 15 of 15)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Interactive Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2505.17016/) (2025)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing](https://mlsanity.com/paper/2604.05014/) (2026)
- [Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales](https://mlsanity.com/paper/2506.19713/) (2025)
- [CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies](https://mlsanity.com/paper/2604.24622/) (2026)
- [WarmPrior: Straightening Flow-Matching Policies with Temporal Priors](https://mlsanity.com/paper/2605.13959/) (2026)
- [FreSca: Scaling in Frequency Space Enhances Diffusion Models](https://mlsanity.com/paper/2504.02154/) (2025)
- [Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal](https://mlsanity.com/paper/2605.27919/) (2026)
- [Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies](https://mlsanity.com/paper/2606.17408/) (2026)
- [Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation](https://mlsanity.com/paper/2606.23420/) (2026)
- [Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation](https://mlsanity.com/paper/2606.20135/) (2026)

## Abstract (arXiv)

Robot actions are temporally correlated trajectories whose frequency components encode motion at different scales with highly non-uniform energy distributions. Yet Flow Matching--based vision-language-action (VLA) models typically generate actions in temporal coordinates, without explicitly modeling or systematically leveraging this frequency heterogeneity. We introduce FreqFM, a frequency-conditioned Flow Matching framework for VLA models. It raises action frequency from an implicit trajectory property to an explicit conditioning dimension that spans the entire generation pipeline. Concretely, in DCT frequency coordinates, FreqFM constructs a spectrum-matched source distribution, adaptively balances the objective across frequencies, and constrains per-frequency guidance residuals using the corresponding reference transport scales. FreqFM integrates into existing Flow Matching action experts without changing the VLA backbone. Across LIBERO, LIBERO-Plus, and VLA-Arena, FreqFM consistently improves performance, including a 9.3-point gain on LIBERO-Plus, and further demonstrates its effectiveness on six real-robot tasks.