Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Haoyu, Li, Zhipeng, Guo, Yiwen, Yu, Tianshu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914311777026048
author Zhang, Haoyu
Li, Zhipeng
Guo, Yiwen
Yu, Tianshu
author_facet Zhang, Haoyu
Li, Zhipeng
Guo, Yiwen
Yu, Tianshu
contents Omni-modal large language models (OLLMs) aim to unify multimodal understanding and generation, yet incorporating speech with 3D facial animation remains largely unexplored despite its importance for natural interaction. A key challenge arises from the representation mismatch between discrete, token-level semantic reasoning in LLMs and the dense, fine-grained temporal dynamics required for 3D facial motion, which makes direct modeling difficult to optimize under limited data. We propose Expressive Omni (Ex-Omni), an open-source omni-modal framework that augments OLLMs with speech-accompanied 3D facial animation. Ex-Omni reduces learning difficulty by decoupling semantic reasoning from temporal generation, leveraging speech units as temporal scaffolding and a unified token-as-query gated fusion (TQGF) mechanism for controlled semantic injection. We further introduce InstructEx, a dataset aims to facilitate augment OLLMs with speech-accompanied 3D facial animation. Extensive experiments demonstrate that Ex-Omni performs competitively against existing open-source OLLMs while enabling stable aligned speech and facial animation generation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07106
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
Zhang, Haoyu
Li, Zhipeng
Guo, Yiwen
Yu, Tianshu
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Omni-modal large language models (OLLMs) aim to unify multimodal understanding and generation, yet incorporating speech with 3D facial animation remains largely unexplored despite its importance for natural interaction. A key challenge arises from the representation mismatch between discrete, token-level semantic reasoning in LLMs and the dense, fine-grained temporal dynamics required for 3D facial motion, which makes direct modeling difficult to optimize under limited data. We propose Expressive Omni (Ex-Omni), an open-source omni-modal framework that augments OLLMs with speech-accompanied 3D facial animation. Ex-Omni reduces learning difficulty by decoupling semantic reasoning from temporal generation, leveraging speech units as temporal scaffolding and a unified token-as-query gated fusion (TQGF) mechanism for controlled semantic injection. We further introduce InstructEx, a dataset aims to facilitate augment OLLMs with speech-accompanied 3D facial animation. Extensive experiments demonstrate that Ex-Omni performs competitively against existing open-source OLLMs while enabling stable aligned speech and facial animation generation.
title Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2602.07106