WISE：世界模型引导的想象调度加速 VLA 后训练

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

Source: arXiv cs.RO·2026-09-04 12:00Publish time unverified

arXiv:2609.03681v1 Announce Type: new Abstract: 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.