SOURCE-LINKED INTELLIGENCE

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Post-training VLA policies typically rely on supervised fine-tuning with costly expert demonstrations or reinforcement learning with expensive and potentially unstable real-world exploration. World models offer a promising alternative by evaluating candidate behaviors through imagined futures, yet effective post-training requires more than accurate prediction: imagination must be scheduled where it is useful, bounded within reliable horizons, and translated into trustworthy policy supervision. In robotic manipulation, the value of imagination varies substantially across execution stages, while

Read original source ↗ Open in workspace

recordType

paper

region

Global