Inhabitant: An Agent Framework for Long-Horizon Human-Scene Interaction with Spatial Control and Quantitative Feedback

Media reports Hugging Face Papers Source language: Chinese

Inhabitant enables a language‑model agent to plan and execute long‑horizon human‑scene interactions with spatial commands, measure deviations, and revise control, achieving high task completion on the Inhabit benchmark.

Full text

Inhabitant enables a language-model agent to plan and execute long-horizon human-scene interactions by specifying motions spatially, measuring deviations, and revising control, achieving high task completion on the Inhabit benchmark.

Sources

← Back to Daily AI Report