Newest papers

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

Qinfan Zhang, Yifan Luo, Haoyuan Shi, Guanlin Liu, Han Dong, Haozhe Shan, Yong Dai, Xiangcong Ren · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29866 · open-access PDF

Chinese

地理结构对于机器人操纵和理解3D世界至关重要。大多数VLA模型依靠当前观测的2D表示,而地理意识的方法往往需要额外的3D信息。然而,从个别观测中独立推断的地理往往被抛弃,而不是积累成一个持久的任务表示。我们的关键见解是,动作生成需要一个紧凑的、任务相关的地理抽象,可以不断更新,而不是在每个步骤进行完整的可渲染的3D重建。

Machine translation (Meta M2M100); the English original follows.

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. However, geometry inferred independently from individual observations is often discarded rather than accumulated into a persistent task representation. Our key insight is that action generation needs a compact, task-relevant geometric abstraction that can be continuously updated, rather than a complete, renderable 3D reconstruction at every step. We introduce GeoMem-

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange