HoliWorld: scalable auto-labeling pipeline turns egocentric video into 3D/4D data
liuziwei7 · x · 2026-10-20
Ziwei Liu's team (NTU) and Ropedia AI introduce HoliWorld, claimed to be the first scalable auto-labeling pipeline that converts egocentric videos into holistic multimodal data — from 3D bounding boxes to 4D object tracking. The project is part of an ecosystem (Holi-World paper on arXiv 2610.26549) linking experience capture, world representation, automated data construction, model learning and independent evaluation. Code and data are on Hugging Face.
Related event: Holi-World: Automating Holistic World Intelligence from Egocentric Video(2 posts)→
More from Embodied
- Wayve demos its Fiat 500e autonomous prototype on Turin's iconic Lingotto rooftop track — alexgkendall · 2026-10-20
- EgoXperience turns egocentric video into world-grounded 3D reconstructions in one forward pass — liuziwei7 · 2026-10-20
- Tesla ties key employee equity to Optimus production milestones in Oct 19 proxy filing — Scobleizer · 2026-10-20
- NVIDIA OmniDreams: real-time generative world model for closed-loop AV simulation, at 16 GB300 per video — yassineyousfi_ · 2026-10-20
- HandsOn Benchmark: 66-Task Dexterous Manipulation Test Shows Best Policy at 29% Success — Tianwei Luo · 2026-10-20
- Sparse Feature Unlearning Reduces State Hallucination in Vision-Language-Action Models — Jiho Lee · 2026-10-20