Newest papers

Holi-World: Building Holistic World Intelligence from Human-Ego Experience

Hao Li, Xiyuan Zheng, Yuanyuan Gao, Yalun Dai, Xinhao Ji, Xuan-Li Chen, Jing Zhao, Fangzhou Hong · 2026 · arXiv

DOI: 10.48550/arXiv.2610.26549 · open-access PDF

Spanish

La experiencia egocéntrica humana ofrece una base rica para aprender cómo está organizado el mundo y cómo cambia a través de la interacción.Realizar este potencial a escala requiere convertir volúmenes crecientes de grabaciones en recursos de aprendizaje que conectan estructura de escena, semántica de objetos y historias de interacción a través de puntos de vista y tiempo, al tiempo que reducimos la dependencia de la costosa anotación manual. Introducimos HOLI-WORLD, un ecosistema integrado que conecta la captura de experiencias, la representación del mundo, la construcción de datos automatizada, el aprendizaje de modelos y la evaluación independiente.

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

Abstract

Human egocentric experience offers a rich foundation for learning how the world is organized and how it changes through interaction. Realizing this potential at scale requires turning growing volumes of recordings into learning resources that connect scene structure, object semantics, and interaction histories across viewpoints and time, while reducing dependence on costly manual annotation. We introduce HOLI-WORLD, an integrated ecosystem connecting experience capture, world representation, automated data construction, model learning, and independent evaluation. To sup- port learning at scale

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26549, 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.txt

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