English(EN) OneLA: Learning Many Worlds from Latent Actions

OneLA框架学习统一潜在动作以实现多样化世界模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了OneLA，一个新颖的框架，旨在为跨领域的世界模型学习统一的控制空间。该方法利用直接从视频中提取的潜在动作，无需显式的动作监督。OneLA采用共享正交字典和通用预测目标来学习这些潜在动作，将动作周期迁移旋转误差降低了24.8%，并将真实场景生成的用户偏好得分提高了20.5%。该框架旨在实现能够从各种视频中学习并可通过此学习到的潜在动作空间进行控制的通用世界模型。 AI

影响通过为多样化的视频数据提供统一的潜在动作空间，实现了更通用的世界模型。

排序理由研究论文，详细介绍了学习世界模型中潜在动作的新框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了学习世界模型中潜在动作的新框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Ziyu Zhu, Zhaoxu Sun, Fan Jiang, Chiyu Wang, Junfeng Ni, Mu Xu · 2026-10-15 04:00

OneLA：从潜在动作中学习多重世界

arXiv:2610.20160v1 Announce Type: new Abstract: Learning world models across diverse domains calls for a unified control space, yet ac- tion interfaces vary across domains and action annotations are often scarce. Latent ac- tions learned directly from videos offer a promising way…

本文如何被排名

报道来源 [1]

OneLA：从潜在动作中学习多重世界

相关实体

相关话题