跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-19AI 評分41

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

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

AI 導讀

HOLI-WORLD 建立整合式生態系統,從第一人稱錄影自動構建大規模學習資源,以提升機器對動態場景和互動的理解。HOLIWORLD-Data 整理約 100 個自採場景,包含約 80K 組 QA 問答對,用於訓練 HOLIWORLD-VL-4B;HOLIWORLD-Bench 則以獨立人工標註的保留錄影評估標註質素及空間、時間理解。

正文

Published on Oct 19

·

Submitted by

leoli

on Oct 20

Authors:

,

,

,

,

,

,

,

,

Abstract

HOLI-WORLD is an integrated ecosystem that automates the construction of large-scale learning resources from egocentric recordings to improve machine understanding of dynamic scenes and interactions.

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.

View arXiv page View PDF Project page GitHub Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.26549 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.26549 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.26549 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co