The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface

arXiv cs.AISeptember 30, 2026en

arXiv:2609.36118v1 Announce Type: new Abstract: Vision-language-action (VLA) policies connect a pretrained vision-language backbone to an action head through a latent interface, but which backbone layers this interface should expose remains unclear. We study single-layer selection and multi-layer fusion for frozen backbones across three pretrained models and two manipulation benchmarks, LIBERO and CALVIN, with three policy-training seeds per configuration. Across three fusion mechanisms and three layer-subset strategies, 47 of 54 configurations underperform the best observed single-layer policy. Our stastical analysis further confirms that fusion's advantage is very limited. However, the bes

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Reglering