U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Xiang, Gao, Feng, Zhang, Yong, Pang, Youxin, Xiaoming, Xu, Kang, Zhuoliang, Wei, Xiaoming, Liu, Yebin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917299263373312
author Deng, Xiang
Gao, Feng
Zhang, Yong
Pang, Youxin
Xiaoming, Xu
Kang, Zhuoliang
Wei, Xiaoming
Liu, Yebin
author_facet Deng, Xiang
Gao, Feng
Zhang, Yong
Pang, Youxin
Xiaoming, Xu
Kang, Zhuoliang
Wei, Xiaoming
Liu, Yebin
contents Full-stack multimodal interaction in real-time is a central goal in building intelligent embodied agents capable of natural, dynamic communication. However, existing systems are either limited to unimodal generation or suffer from degraded reasoning and poor cross-modal alignment, preventing coherent and perceptually grounded interactions. In this work, we introduce U-Mind, the first unified system for high-intelligence multimodal dialogue that supports real-time generation and jointly models language, speech, motion, and video synthesis within a single interactive loop. At its core, U-Mind implements a Unified Alignment and Reasoning Framework that addresses two key challenges: enhancing cross-modal synchronization via a segment-wise alignment strategy, and preserving reasoning abilities through Rehearsal-Driven Learning. During inference, U-Mind adopts a text-first decoding pipeline that performs internal chain-of-thought planning followed by temporally synchronized generation across modalities. To close the loop, we implement a real-time video rendering framework conditioned on pose and speech, enabling expressive and synchronized visual feedback. Extensive experiments demonstrate that U-Mind achieves state-of-the-art performance on a range of multimodal interaction tasks, including question answering, instruction following, and motion generation, paving the way toward intelligent, immersive conversational agents.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23739
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation
Deng, Xiang
Gao, Feng
Zhang, Yong
Pang, Youxin
Xiaoming, Xu
Kang, Zhuoliang
Wei, Xiaoming
Liu, Yebin
Computer Vision and Pattern Recognition
Full-stack multimodal interaction in real-time is a central goal in building intelligent embodied agents capable of natural, dynamic communication. However, existing systems are either limited to unimodal generation or suffer from degraded reasoning and poor cross-modal alignment, preventing coherent and perceptually grounded interactions. In this work, we introduce U-Mind, the first unified system for high-intelligence multimodal dialogue that supports real-time generation and jointly models language, speech, motion, and video synthesis within a single interactive loop. At its core, U-Mind implements a Unified Alignment and Reasoning Framework that addresses two key challenges: enhancing cross-modal synchronization via a segment-wise alignment strategy, and preserving reasoning abilities through Rehearsal-Driven Learning. During inference, U-Mind adopts a text-first decoding pipeline that performs internal chain-of-thought planning followed by temporally synchronized generation across modalities. To close the loop, we implement a real-time video rendering framework conditioned on pose and speech, enabling expressive and synchronized visual feedback. Extensive experiments demonstrate that U-Mind achieves state-of-the-art performance on a range of multimodal interaction tasks, including question answering, instruction following, and motion generation, paving the way toward intelligent, immersive conversational agents.
title U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.23739