<ul><li>Diffusion models have gained attention in robotics for generating multi-modal distributions of system states and behaviors.</li><li>Ensuring precise control over generated outcomes without compromising realism remains a challenge in diffusion models.</li><li>A novel framework is proposed to enhance controllability in diffusion models by leveraging multi-modal prior distributions and enforcing strong modal coupling.</li><li>The framework achieves superior fidelity, diversity, and controllability in motion prediction and multi-task control experiments, providing a reliable and scalable solution for controllable motion generation in robotics.</li></ul>

Controllable Motion Generation via Diffusion Modal Coupling

Discover more