English(EN) GeoMem-VLA: Internalizing 3D Scene Understanding into Temporal Memory for Vision-Language-Action Models

新的GeoMem-VLA框架将3D场景理解内化，用于机器人控制

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-22 04:00

研究人员开发了GeoMem-VLA，一个用于视觉-语言-动作模型的新框架，它将3D场景理解内化为时序记忆。与现有模型通常会丢弃几何信息或需要显式3D数据不同，GeoMem-VLA使用随时间更新的专用几何令牌。这种方法通过在每个步骤中无需重建整个3D场景即可提供紧凑、与任务相关的几何抽象，从而实现更有效的机器人控制。该框架在LIBERO和RoboTwin等基准测试以及实际机器人任务中都取得了很高的成功率。 AI

影响内化和记忆3D场景理解是机器人控制的一种有前景的方法，有望提高复杂操作任务的性能。

排序理由详细介绍机器人新模型/框架的学术论文。[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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍机器人新模型/框架的学术论文。[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, product; 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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Qinfan Zhang, Yifan Luo, Haoyuan Shi, Guanlin Liu, Han Dong, Haozhe Shan, Yong Dai, Xiangcong Ren, Xiaozhu Ju · 2026-10-22 04:00

GeoMem-VLA: Internalizing 3D Scene Understanding into Temporal Memory for Vision-Language-Action Models

arXiv:2610.29866v1 Announce Type: new Abstract: Geometric structure is essential for robotic manipulation and understanding the 3D world. Most VLA models rely on 2D representations of current observations, while geometry-aware approaches often require additional 3D information. H…

本文如何被排名

报道来源 [1]

GeoMem-VLA: Internalizing 3D Scene Understanding into Temporal Memory for Vision-Language-Action Models

相关实体

相关话题