Towards Interactive Intelligence for Digital Humans
This work addresses the need for more intelligent and adaptive digital humans in applications like virtual assistants or entertainment, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of creating digital humans with interactive intelligence by introducing Mio, an end-to-end framework that integrates cognitive reasoning and multimodal embodiment, achieving superior performance compared to state-of-the-art methods across all evaluated dimensions.
We introduce Interactive Intelligence, a novel paradigm of digital human that is capable of personality-aligned expression, adaptive interaction, and self-evolution. To realize this, we present Mio (Multimodal Interactive Omni-Avatar), an end-to-end framework composed of five specialized modules: Thinker, Talker, Face Animator, Body Animator, and Renderer. This unified architecture integrates cognitive reasoning with real-time multimodal embodiment to enable fluid, consistent interaction. Furthermore, we establish a new benchmark to rigorously evaluate the capabilities of interactive intelligence. Extensive experiments demonstrate that our framework achieves superior performance compared to state-of-the-art methods across all evaluated dimensions. Together, these contributions move digital humans beyond superficial imitation toward intelligent interaction.