Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies
Vision-language-action (VLA) policies based on flow matching generate action chunks through repeated evaluations of an action expert. Increasing the number of integration steps raises inference cost, but does not necessarily improve closed-loop success. We propose Coda, which reallocates part of this integration budget...
Zhi-Peng Tang, Xin-Da Chen, Wei-Ning Rao et al.
· 0 citations