HuggingFace Daily Papers·· 1 天前
WAVE-0：用轻量潜在未来预测连接 VLA 策略与 WAM
WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction
AI 导读
WAVE-0 框架通过轻量潜在世界模型连接 VLA 与 WAM，让预判的动作后果直接引导动作生成。其 257M 世界模型无需像素重建或大规模视频预训练，在 RoboTwin 2.0 上成功率达 91.47%、LIBERO 达 98.7%，并将真实任务中 π0.5 的成功率从 38.3% 提升至 73.3%。
正文
Abstract:Vision-language-action (VLA) policies excel at generalist robotic manipulation but generate actions without explicitly modeling their environmental consequences. World action models (WAMs) incorporate future prediction, yet most rely on costly video generation, while latent alternatives either use predicted futures only as auxiliary targets or infer latent actions from suboptimal visual transitions through costly large-scale video pretraining. We introduce WAVE-0 (World-model-Augmented VLA Execution), a framework that bridges VLAs and WAMs through a lightweight latent world model. By connecting the semantic understanding of pretrained VLAs with explicit future prediction, WAVE-0 allows anticipated action consequences to directly guide action generation. Built on a pretrained VLA, its 257M world model translates VLM-generated latent action plans into predicted future representations that condition the action expert, unifying latent planning, future prediction, and action generation. The world model is trained directly on ground-truth robot actions with a counterfactual ranking objective, requiring neither pixel reconstruction nor large-scale video pretraining. WAVE-0 achieves success rates of 91.47% on RoboTwin 2.0 and 98.7% on LIBERO, along with 88.0%, 61.4%, and 75.0% on LIBERO-Plus, LIBERO-Pro, and LIBERO-Para, respectively. On real-world tasks, it improves the success rate of $\pi_{0.5}$ from 38.3% to 73.3%. These results demonstrate strong manipulation performance and generalization across diverse distribution shifts.
| Subjects: | Robotics (cs.RO) |
| Cite as: | arXiv:2610.18568 [cs.RO] |
| (or arXiv:2610.18568v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18568 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haomin Wang H. Wang [view email]
[v1]
Tue, 13 Oct 2026 15:37:50 UTC (14,718 KB)
来源：HuggingFace Daily Papers · arxiv.org