Search papers, labs, and topics across Lattice.
Archon is introduced as a unified multimodal model for generating digital humans, addressing the challenge of integrating text, audio, motion, and visual content. The model employs modality-specific tokenizers and a native autoregressive architecture pretrained on synchronized multimodal data and 72 tasks to capture holistic joint distributions. Key to Archon is a memory-efficient semantic video reparameterization for 4x token reduction and a "Thinking in Modality" approach for enhanced fidelity and control in cross-modal tasks.
Forget disjointed avatar components – Archon lets you generate complete, synchronized digital humans across text, audio, motion, and visuals with a single unified model.
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/.
