Rimvydas Rubavicius

Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs

This work proposes a framework that exposes backbone depth V, action expert depth A, and denoising steps $D$ as three jointly configurable compute axes in a VLA, and introduces a KV Cache synthesis mechanism that manages the missing keys and values of the skipped backbone layers, allowing the action expert to exit deep...