World2HOSI: Multi-expert orchestration generates long-horizon human-object-scene interaction data
What happened
Researcher Jiushu Li and colleagues propose World2HOSI, a multi-expert orchestration framework that generates continuous human-object-scene interaction (HOSI) data from 3D Gaussian Splatting (3DGS) scenes and natural-language instructions. The paper says it achieves the best task completion and interaction quality on the HOSI tasks it evaluated, and that it generates more diverse data. The paper says the method reduces physical artifacts through persistent scene state, bounded residual optimization, and contact-driven physics simulation. These results are self-reported and have not been independently verified.
AI-written from the coverage · updated 2026-10-21
Coverage timeline
Follow the coverage to see the story from different sides.
- arXiv Game AIWorld2HOSI uses a multi-expert harness to generate long-horizon human-object-scene interaction data
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.