SOURCE-LINKED INTELLIGENCE

Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Vision-Language-Action (VLA) policies commonly run Vision-Language Model (VLM) backbones with billions of parameters at every policy inference, which costs latency and energy. We revisit a decoupled alternative for multi-task manipulation: separate vision and language encoders whose representations condition a compact action head. We run a standardized comparison that varies the vision encoder, the language encoder, and the action head while holding the demonstrations, the training-step budget, the tasks, the evaluation protocol, and the measurement platform fixed, against seven VLA baselines.

Read original source ↗ Open in workspace

recordType

paper

region

Global