Towards Interactive Intelligence for Digital Humans
By: Yiyi Cai , Xuangeng Chu , Xiwei Gao and more
Potential Business Impact:
Makes digital people act and learn like real ones.
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.
Similar Papers
Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans
CV and Pattern Recognition
Creates lifelike digital people that talk and react instantly.
OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation
CV and Pattern Recognition
Makes video characters act with real feelings.
AIVA: An AI-based Virtual Companion for Emotion-aware Interaction
CV and Pattern Recognition
AI understands your feelings to talk and act better.