Think with Motion: A Unified Understanding and Generation Framework for Individual and Interactive Human Motion

Text-driven human motion modeling bridges high-level semantics with complex physical dynamics. For interactive motion generation, prevailing methods leverage coupled representations in the raw motion space, struggling to interpret underlying social intent through interactive text-conditioned descriptions. Meanwhile, emerging motion–language models unify motion understanding and generation, whereas the shared parameters across both tasks induce severe interference. To address these issues, we propose $I^2\text{MoT}$, a simple and unified architecture for individual and interactive motion understanding and generation. Specifically, we introduce a relation-decoupled representation that factorizes interactions into individual movements and relative geometry. $I^2\text{MoT}$ further introduces a task-specific Mixture-of-Transformers architecture to mitigate interference between motion understanding and generation. We additionally establish a participant-level Chain-of-Thought reasoning mechanism, enabling motion understanding to explicitly guide interactive motion generation. Extensive experiments on HumanML3D and InterHuman datasets demonstrate that $I^2\text{MoT}$ achieves superior performance across all motion modeling tasks.