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.
@article{arxiv.2512.13674,
title = {Towards Interactive Intelligence for Digital Humans},
author = {Yiyi Cai and Xuangeng Chu and Xiwei Gao and Sitong Gong and Yifei Huang and Caixin Kang and Kunhang Li and Haiyang Liu and Ruicong Liu and Yun Liu and Dianwen Ng and Zixiong Su and Erwin Wu and Yuhan Wu and Dingkun Yan and Tianyu Yan and Chang Zeng and Bo Zheng and You Zhou},
journal= {arXiv preprint arXiv:2512.13674},
year = {2026}
}