SOURCE-LINKED INTELLIGENCE

Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Pretrained driving vision-language models (VLMs) integrate visual, route, language, and driving context into rich driving priors, yet their representation objectives remain separated from continuous driving planning. Existing methods typically begin trajectory generation only after the VLM has formed a final condition, leaving depth-wise condition computation outside the stepwise formation of trajectory state. We introduce DiffAdapterVLA, which realizes Planning in the Backbone: it injects explicit trajectory tokens into selected VLM late layers, bringing trajectory state into backbone forward

Read original source ↗ Open in workspace

recordType

paper

region

Global