FReD-VLA: A Vision-Language-Action Model with Flow Matching-Initialized Diffusion

Deploying vision-language-action (VLA) models for bimanual manipulation in real-world environments requires robots to generate accurate actions with low latency to respond to changing surroundings. State-of-the-art methods usually adopt diffusion- or flow matching-based approaches for continuous action generation. Despite promising results, balancing accuracy and latency still remains challenging. Diffusion models can generate accurate actions, but repeated denoising increases computation and latency. One-step flow matching is efficient, but its actions tend to be inaccurate for fine-grained manipulation. In this paper, we propose a Vision-language-Action model with Flow Matching initialized Diffusion (FReD-VLA), which combines fast flow-based generation with diffusion-based correction. Given visual observations, language instructions, and robot states, a flow matching model first generates a coarse action sequence. The coarse action sequence is then refined by a diffusion model through Action Distribution Calibrator, enabling refinement from a well-initialized intermediate diffusion state rather than the fully-corrupted beginning state. Empirically, on Maniskill PickCube-v1, our model achieves a mean minimum end-effector-to-cube distance of 10.8 mm, with $75.3\%$ reduction than the 43.7 mm measured for pure Diffusion. In offline evaluation, one diffusion step reduces the joint mean absolute error of a one-step flow proposal from $1.176^{\circ }$ to $0.620^{\circ }$. This is a 47.3% reduction. With one flow evaluation and one diffusion evaluation, FReD-VLA achieves an action-generation latency of 37.0 ms, excluding shared multimodal encoding. This provides a $4.1\times$ speedup over five-step diffusion with comparable action accuracy. Real-robot tests further demonstrate dynamic bimanual assembly after adaptation with about 20–30 human demonstrations per behavior.