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, Zhaoxi Chen, Ziwei Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26549 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

وتتطلب تحويل كميات متزايدة من الإشارات إلى موارد التعلم التي تتوافق مع هيكل السيناريو، ومواصفات التفاعل المشترك بين وجهات النظر والزمان، مع تقليل اعتمادها على التوصيات الصارمة من خلال التفاعل.نحن نقدم HOLI-WORLD، منظومة متكاملة تتوافق مع قصص التفاعل، ومواصفات العالم، وتكوين بيانات تلقائية، وتعلم النماذج، والتقييم المستقل.للمساعدة في التعلم على نطاق واسع، يقوم HOLIWORLD-Foundry بتجميع الإشارات الصارمة والتفاعلية بشكل تلقائي لتكوين الإشارات التي تتوافق بشكل تلقائي مع هيكل السيناريو المستمر والمواصفات المتقدمة مع الإشارات التفاعل

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, HOLIWORLD-Foundry combines complementary static and dynamic perception to automatically construct world records that connect persistent scene structure and evolving object states with interaction histories and supporting observations. HOLIWORLD-Data organizes these records from approximately 100 self-collected scenes into grounded learning resources, including approximately 80K QA pairs used to train HOLIWORLD-VL-4B. Independent human annotations of heldout recordings form HOLIWORLD-Bench, supporting evaluation of both annotation quality and learned spatial and temporal understanding. Experiments on ScanNet, ScanNet++, Aria Digital Twin, and HOLIWORLD-Bench demonstrate strong performance in static perception and dynamic tracking, while training on HOLIWORLD-Data substantially improves HOLIWORLD-VL-4B's spatial and temporal reasoning on HOLI- WORLD-Bench and EgoDynamic4D. HOLIWORLD provides a practical foundation for expanding learning resources from the continuous flow of human experience and advancing machine understanding of the dynamic world.

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

Topics: Computer science, Viewpoints, Artificial intelligence, Perception, Construct (python library), Object (grammar)

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