cs.CVNov 16, 2026

FAVR: Flow-Aware Visual Residual Alignment for Vision-Language-Action Policies

Authors: Qixuan Wu, Xiaole Yang, Yuguang Yang, Canyu Chen, Linlin Yang, Haixia Pan, Guodong Guo, Baochang Zhang

Organizations: School of Artificial Intelligence, Beihang University, Beijing, China · School of Software, Beihang University, Beijing, China · School of Electronic and Information Engineering, Beihang University, Beijing, China · National College for Excellent Engineers, Beihang University, Beijing, China · 

Abstract

Pretrained video representations provide rich temporal information for robotic manipulation, yet effectively integrating them into existing vision-language-action (VLA) policies remains challenging. We present Flow-Aware Visual Residual Alignment (FAVR), a lightweight framework for flow-aware visual conditioning of frozen VLA policies. FAVR maintains a compact temporal visual state through linear Test-Time Training (TTT) and retrieves action-conditioned visual features throughout flow-based action generation. By exploiting the affine structure of the frozen action head, we explicitly characterize how injected visual features influence predicted action velocities and formulate flow-aware channel selection as a box-constrained optimization problem. We develop a FISTA-based solver for joint gate optimization and derive an efficient closed-form approximation through diagonalization and rescaling. With only 1.74-2.19M trainable parameters and 5,000 adaptation steps, FAVR improves pretrained VLA policies across benchmarks. On RoboTwin 2.0, FAVR improves LingBot-VLA from 87.12% to 90.04% under clean conditions and from 86.88% to 89.38% under randomized conditions. A controlled ablation on five RoboTwin tasks further shows that flow-aware gating increases average success from 72.0% with a gate shared across flow steps to 82.0%, demonstrating the benefit of adapting visual conditioning throughout action generation.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. NF-VLA: A Normalizing-Flow Baseline for Vision-Language-Action Learning

    Nov 15, 2026Ruichen Deng, Qinyu Zhao, Yong-Hyun Park +3Flow-Based VLAsFlow-Based Policy Learning

  2. CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies

    Apr 27, 2026Fan Du, Feng Yan, Jianxiong Wu +8Robotic ControlEfficient VLA Inference

  3. Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies

    Sep 18, 2026Zhipeng Tang, Xinda Chen, Weining Rao +5Flow-Based VLAsEfficient VLA Inference