SOURCE-LINKED INTELLIGENCE

ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Vision-Language-Action (VLA) policies are commonly adapted to new manipulation settings through additional gradient updates, which limits rapid deployment when task-specific data or compute is scarce. We present ICI-VLA, a training and retrieval framework that equips a text-action VLM with few-shot test-time adaptation through in-context demonstrations. Unlike mainstream VLA designs based on action-specific multimodal fusion, ICI-VLA retains the native text-generation interface. ICI-VLA updates its parameters only during offline training; at inference, the policy remains fixed and conditions a

Read original source ↗ Open in workspace

recordType

paper

region

Global