Should the Action Expert Train the VLM? Action-Token Supervision and Gradient Routing in Mixture-of-Transformer VLAs

arXiv:2611.05249 · cs.RO · Submitted 2026-11-03 · Read on arXiv

cs.RO

Submitted: 2026-11-03

Updated: 2026-11-03

Code: https://github.com/NVlabs/alpasim

Project page: https://mot-vla-gradient-routing.github.io/ABSTRACT

Terminology

Sources

Related papers