Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bao, Chong, Liu, Shichen, Yu, Lijun, Futschik, David, Moschoglou, Stylianos, Srivastava, Shefali, Bai, Ziqian, Tan, Feitong, Zhang, Guofeng, Cui, Zhaopeng, Fanello, Sean, Zhang, Yinda
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.30311
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918530094465024
author Bao, Chong
Liu, Shichen
Yu, Lijun
Futschik, David
Moschoglou, Stylianos
Srivastava, Shefali
Bai, Ziqian
Tan, Feitong
Zhang, Guofeng
Cui, Zhaopeng
Fanello, Sean
Zhang, Yinda
author_facet Bao, Chong
Liu, Shichen
Yu, Lijun
Futschik, David
Moschoglou, Stylianos
Srivastava, Shefali
Bai, Ziqian
Tan, Feitong
Zhang, Guofeng
Cui, Zhaopeng
Fanello, Sean
Zhang, Yinda
contents Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained on synchronized modalities and 72 diverse tasks to model holistic joint distributions. To address the token explosion challenge in high-fidelity talking videos, we introduce a memory-efficient semantic video reparameterization, achieving 4x token reduction while preserving fine-grained dynamics, coupled with a semantic-driven video diffusion decoder. We further propose a "Thinking in Modality" that decomposes ambiguous cross-modal tasks into stepwise thinking in an alternative chain of modality, progressively enhancing fidelity and controllability. Extensive experiments demonstrate that Archon achieves superior or comparable performance across diverse digital human generation tasks, validating the effectiveness of our unified framework. Project page: https://zju3dv.github.io/archon/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30311
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Archon: A Unified Multimodal Model for Holistic Digital Human Generation
Bao, Chong
Liu, Shichen
Yu, Lijun
Futschik, David
Moschoglou, Stylianos
Srivastava, Shefali
Bai, Ziqian
Tan, Feitong
Zhang, Guofeng
Cui, Zhaopeng
Fanello, Sean
Zhang, Yinda
Computer Vision and Pattern Recognition
Artificial Intelligence
Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained on synchronized modalities and 72 diverse tasks to model holistic joint distributions. To address the token explosion challenge in high-fidelity talking videos, we introduce a memory-efficient semantic video reparameterization, achieving 4x token reduction while preserving fine-grained dynamics, coupled with a semantic-driven video diffusion decoder. We further propose a "Thinking in Modality" that decomposes ambiguous cross-modal tasks into stepwise thinking in an alternative chain of modality, progressively enhancing fidelity and controllability. Extensive experiments demonstrate that Archon achieves superior or comparable performance across diverse digital human generation tasks, validating the effectiveness of our unified framework. Project page: https://zju3dv.github.io/archon/.
title Archon: A Unified Multimodal Model for Holistic Digital Human Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.30311