Archon: A Unified Multimodal Model for Holistic Digital Human Generation
This work addresses the challenge of creating a single model for all digital human generation modalities, offering a unified framework for immersive interaction applications.
Archon is a unified multimodal model for holistic digital human generation that integrates seven modalities (text, audio, motion, visual) using modality-specific tokenizers and a pretrained autoregressive model. It achieves superior or comparable performance across diverse tasks, with a 4x token reduction for high-fidelity talking videos via semantic video reparameterization.
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/.