Runjia Li, Kam Woh Ng, Minghao Chen, Junlin Han, Jianyuan Wang, Zhaochong An, Juan-Manuel Perez-Rua, Andrea Vedaldi · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28554 · open-access PDF
비디오 세계 모델의 성공에도 불구하고, 여러 에이전트로 확장하는 것은 여러 에이전트 특정 비디오 스트림을 생성하는 것이 필요하기 때문에 어렵습니다.이 격차를 해결하기 위해, 우리는 에이전트 위치의 단순한 변경으로 인해 완전히 변할 수있는 OverSeer 세계 모델을 소개합니다.우리는 공간에서 보조 뷰를 고정함으로써 보조 뷰가 세계 중심의 대표를위한 프록시 역할을한다고 제안합니다.
Machine translation (Meta M2M100); the English original follows.
Despite the success of video world models, extending them to multiple agents is difficult because it requires generating several agent-specific video streams that are consistent in time and between agents. To address this gap, we introduce OverSeer, a multi-agent world model that augments egocentric agent views with auxiliary camera views. We suggest that, by fixing the auxiliary views in space, they act as a proxy for a world-centric representation: Unlike the agents' views, which can change entirely due to a simple change in agent position, changes in the auxiliary views directly map to loca
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=2610.28554, 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