AI Paper Atlas

Research map / Video / Video generation

Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback

Xingpei Ma, Shenneng Huang, Jiaran Cai, Yuansheng Guan, Shen Zheng, Hanfeng Zhao, Qiang Zhang, Shunsi Zhang

AAAI 2026 · Video › Video generation · approach: Talking face generation · 1 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 Flow-DPO reward feedback (Sync-C based pairs) (ablation)Ours · HDTFFID: 29.05 -> 27.63Improved
add DPO reward feedback (ablation)Ours · CelebV-HQFID: 76.25 -> 66.11Improved
add DPO reward feedback (ablation)Ours · HDTFSync-C: 7.89 -> 8.15Improved
add DPO reward feedback (ablation)Ours · CelebV-HQSync-C: 5.28 -> 5.49Improved
add DPO reward feedback (ablation)Ours · CelebV-HQFVD: 152.33 -> 133.78Improved
use LoRA chunked-latent long video training instead of OmniAvatar/Hunyuan extension (ablation)Ours · long video generationqualitativeImproved
compare with MultiTalk on lip syncOurs · HDTFSync-C: 8.57 vs 8.15Hurt
compare with MultiTalk on naturalnessOurs · User studyNaturalness MOS: 3.93 vs 3.90No clear effect

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