Towards Interactive Intelligence for Digital Humans

TL;DR

This paper introduces Mio, a comprehensive framework for digital humans with interactive intelligence, combining multimodal embodiment and cognitive reasoning to enable realistic, adaptive, and personality-aligned interactions.

Contribution

The paper presents Mio, an end-to-end multimodal framework with five modules, and establishes a new benchmark for evaluating interactive intelligence in digital humans.

Findings

Mio outperforms existing methods in interaction quality.

The framework enables personality-aligned expression and self-evolution.

Extensive experiments validate superior performance across multiple metrics.

Abstract

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.