DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

ArXi:2603.29844v1 Announce Type: cross The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping vision-language features to low-level actions. This paradigm underutilizes the VLM's potential in high-level decision making and