Skip to content
arXiv Game AI· Jiushu Li·· 2026-10-20PickAI score35

World2HOSI uses a multi-expert harness to generate long-horizon human-object-scene interaction data

World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation

AI summary

World2HOSI is a multi-expert harness framework that generates continuous human-object-scene interaction (HOSI) data from 3DGS scenes and natural language instructions. The paper reports that it achieves the best task completion and interaction quality on the evaluated HOSI tasks, and produces more diverse data. The method reduces physical artifacts through persistent scene state, bounded residual optimization, and contact-driven physics simulation.

Why it matters

The paper orchestrates existing expert models within a unified scene state, offering a transferable idea for generating long-horizon interactions where training data is scarce.

Source: arXiv Game AI · arxiv.org