TL; DR: APT factorizes the VLA policy into a Vision-Action (VA) prior and a language-conditioned VLA likelihood, and pretrains the action expert as the VA prior on vision-action pairs from a frozen VLM. A layer-wise gated fusion mechanism then injects language tokens into the pretrained action expert, preserving the visuomotor prior while enabling instruction following. APT delivers consistent gains on OOD language instructions and compositional tasks.

🏆 Highlights

🔍 Key Findings: continuous-action VLA policies start from a randomly initialized action expert and learn from imbalanced VLA data, producing noisy gradients that corrupt the VLM backbone and collapse to visual shortcuts.

✨ Key Insights:

• Bayesian factorization of the VLA policy: