ResearchOct 27, 2026, 00:00 UTC

Hugging Face paper proposes World-in-Context for interactive video world modeling

The 5B model reaches navigation performance close to a 22B baseline (81.5 vs 81.6) and a 93.8% perspective-switching success rate on WBench, using explicit view, action and camera tokens.

LabHugging Face
ModelWorld-in-Context-5B
ModelEchoWM
Topicresearch
Topicvideo

1outlet ran itRead at Hugging Face Papers

Status: Research
Published: Oct 27, 2026, 00:00 UTC That day
Outlets: 1
Written by: Claude How

Every outlet that ran it 1 article

Oct 27, 2026, 00:00 UTC
Hugging Face PapersResearchLead
World-in-Context: Interactive Video World Modeling with In-Context Conditioning

All news