AI Paper Atlas

Research map / Video / Video generation

Archon: A Unified Multimodal Model for Holistic Digital Human Generation

Chong Bao, Shichen Liu, Lijun Yu, David Futschik, Stylianos Moschoglou, Shefali Srivastava, Ziqian Bai, Feitong Tan, Guofeng Zhang, Zhaopeng Cui, Sean Fanello, Yinda Zhang

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Thinking in Modality (intermediate shape, expression, semantic video and description generation) (ablation)Archon · CelebV-HQ speech-driven video generationFID: 13.76 -> 6.818Improved
add Thinking in Modality (ablation)Archon · CelebV-HQ speech-driven video generationFVD: 128.1 -> 93.81Improved
add Thinking in Modality (ablation)Archon · CelebV-HQ speech-driven video generationSync-C: 3.088 -> 5.210Improved
add Thinking in Modality (ablation)Archon · HDTF speech-driven video generationFID: 13.43 -> 5.779Improved
add Thinking in Modality (ablation)Archon · HDTF speech-driven video generationSync-C: 4.478 -> 6.198Improved
use a single unified model instead of an ensemble of modality experts with equal parameters (ablation)Archon · CelebV-HQ speech-driven video generationFVD: 170 -> 93.81Improved
use a single unified model instead of an ensemble of experts (ablation)Archon · CelebV-HQ speech-driven video generationSync-C: 3.209 -> 5.210Improved
use a single unified model instead of an ensemble of experts (ablation)Archon · HDTF speech-driven video generationFVD: 199.5 -> 81.64Improved
use a single unified model instead of an ensemble of experts (ablation)Archon · CelebV-HQ speech-driven video generationFID: 7.279 -> 6.818Improved
use Archon (unified, no finetuning) instead of Hallo3 trained on the benchmarkArchon vs Hallo3 · CelebV-HQ speech-driven video generationSync-C: 5.429 -> 5.210Hurt
use Archon instead of Hallo3Archon vs Hallo3 · HDTF speech-driven video generationFID: 12.78 -> 5.779Improved
use Archon instead of FaceTTS for image-conditioned TTSArchon vs FaceTTS · CelebV-HQ image-conditioned text-to-speechMCD-DTW: 7.9383 -> 8.918Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy