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
기하학적 구조는 로봇 조작 및 3D 세계 이해에 필수적입니다. 대부분의 VLA 모델은 현재 관찰의 2D 표현에 의존하지만, 기하학에 의식하는 접근 방식은 종종 추가 3D 정보를 필요로합니다.그러나 개별 관찰에서 독립적으로 추론 된 기하학은 종종 지속적인 작업 표현으로 축적되는 대신에 버려집니다.우리의 핵심 통찰력은 액션 생성은 각 단계에서 완전하고 렌더링 가능한 3D 재구성 대신에 지속적으로 업데이트 될 수있는 컴팩트하고 작업 관련 기하학적 추상이 필요하다는 것입니다.
Machine translation (Meta M2M100); the English original follows.
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
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29866, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange