HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 2026-05-26精选AI 评分72
GE-Sim 2.0：面向机器人操作的全面闭环视频世界模拟器路线图
AI 导读
GE-Sim 2.0是一个用于机器人操作的闭环视频世界模拟器。它基于动作条件视频生成框架，并使用数千小时涵盖遥操作与接触交互等真实世界数据进行重新训练，提升了动作跟随与轨迹覆盖能力。其核心新增三个模块：从视频潜变量解码本体感受状态的“状态专家”；为生成轨迹评分并提供成功信号与奖励的“世界评判”；以及能实现快速轨迹生成的加速框架。该模型仅2B参数，在WorldArena排行榜上位列第一，优于专用模型与闭源生成器，其训练出的策略能转化为实际世界性能提升。
推荐理由
过去机器人策略训练卡在仿真到真机的鸿沟上，GE-Sim 2.0 把视频生成、状态提取和自动评估闭环了，策略迭代效率可能翻倍，搞具身智能的很值得蹲一下。
正文
Authors:Boxiang Qiu, Liliang Chen, Yue Liao, Nan Wang, Lintao Wang, Jiayi Luo, Wenzhi Zhao, Shengcong Chen, Di Chen, Ye Li, Chen Gao, Shuicheng Yan, Si Liu, Maoqing Yao, Guanghui Ren
Abstract:We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation framework of Genie Envisioner, GE-Sim 2.0 is re-trained on thousands of hours of real-world robot data spanning teleoperation, contact-rich interaction, and on-robot policy deployment, substantially improving action-following fidelity and trajectory coverage. On top of this foundation, three new modules close the loop from video simulation to policy learning: a state expert that decodes proprioceptive state from video latents to support next-chunk prediction by downstream VLA policies; a world judge that scores generated rollouts against task instructions, yielding machine-verifiable success signals and rewards in place of manual inspection; and an acceleration framework that delivers a 25-frame rollout in 2.3 seconds on a single H100, with up to 4* frame skipping at inference for long-horizon evaluation. GE-Sim 2.0 tops the public WorldArena leaderboard at only 2B parameters, outperforming both dedicated robotic world models and closed-source general video generators, and policies trained against its rollouts and rewards translate into measurable real-world gains, establishing GE-Sim 2.0 as a practical platform for scalable evaluation and closed-loop learning of manipulation policies.
| Subjects: | Robotics (cs.RO) |
| Cite as: | arXiv:2605.27491 [cs.RO] |
| (or arXiv:2605.27491v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2605.27491 arXiv-issued DOI via DataCite |
Submission history
From: Yue Liao [view email]
[v1]
Tue, 26 May 2026 16:23:05 UTC (15,396 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org