HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 2026-06-11精选AI 评分75
WEAVER：一种更优、更快、更长的机器人操作世界模型
AI 导读
WEAVER是一种多视图世界模型架构，通过流匹配损失训练预测未来潜变量和奖励值，满足保真度、一致性和效率三个要求。在机器人操作任务上，WEAVER在政策评估中与真实成功率的相关系数ρ=0.870，在π₀.₅基础模型基础上实现政策改进成功率提升38%，测试时规划成功率提升14%，且速度比先前世界模型快5–10倍。在分布外场景下表现也优于先前世界模型。代码、模型和视频已开源。
推荐理由
世界模型在机器人操控上第一次同时跑通了「高保真、长时一致、高推理效率」这三个硬指标，真机实验把成功率拉高38%，代码模型全开源，搞具身智能的值得认真读。
正文
Abstract:The potential impacts of world models (WMs, i.e., learned simulators) on robotics are far-reaching -- policy evaluation, policy improvement, and test-time planning -- all with limited real-world interaction. To unlock these downstream capabilities, a WM needs to jointly satisfy three desiderata: $\textit{(i)}$ fidelity (i.e., producing simulated trajectories that correlate with reality), $\textit{(ii)}$ consistency (i.e., producing simulated trajectories that are coherent over long horizons), and $\textit{(iii)}$ efficiency (i.e., producing simulated trajectories quickly). We propose WEAVER (World Estimation Across Views for Embodied Reasoning): a WM architecture that simultaneously achieves all three desiderata, providing state-of-the-art results on robotic manipulation tasks. WEAVER is a multi-view WM trained to predict future latents and reward values via a flow-matching loss. We distill the key design decisions across model architecture, memory, and prediction objectives required to unlock the kinds of long-horizon dynamic manipulation tasks that have confounded prior world modeling approaches. We apply WEAVER in robotic hardware, demonstrating its effectiveness at policy evaluation ($\rho$=0.870 correlation with real-world success rate), policy improvement (real-world success rate improvement of $38\%$ on top of the $\pi_{0.5}$ robot foundation model), and test-time planning (real-world success rate improvement of $14\%$ with a $5-10\times$ speedup over prior WMs). WEAVER also demonstrates better performance than prior WMs when evaluated on out-of-distribution scenarios. Code, models, and videos at: this https URL .
| Subjects: | Robotics (cs.RO) |
| Cite as: | arXiv:2606.13672 [cs.RO] |
| (or arXiv:2606.13672v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2606.13672 arXiv-issued DOI via DataCite |
Submission history
From: Arnav Kumar Jain [view email]
[v1]
Thu, 11 Jun 2026 17:59:15 UTC (6,299 KB)
[v2]
Tue, 16 Jun 2026 20:54:22 UTC (6,299 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org