AI Paper Atlas

Research map / Video / Video generation

Emotion-Conditioned Motion Sub-spaces with Flow Matching for Real-Time Audio-Driven Talking Heads

Haoyu Wang, Xiaozhe Xin, Xiaoyu Qin, Meiguang Jin, Junfeng Ma, Dan Xu, Jia Jia

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
Remove emotion-conditioned sub-spaces (use motion dictionary directly) (ablation)Ours · MEADemotion accuracy (%): 82.05 -> 64.10Improved
Choose random bases instead of learned emotion sub-spaces (ablation)Ours · MEADemotion accuracy (%): 82.05 -> 45.00Hurt
Use learned emotion sub-spaces vs random bases (ablation)Ours · MEADFVD: 84.30 -> 50.39Improved
Use layer-progressive cross-attention fusion instead of naive concatenation (ablation)Ours · MEADemotion accuracy (%): 33.33 -> 82.05Improved
Use layer-progressive fusion instead of self-attention fusion (ablation)Ours · MEADFVD: 64.30 -> 50.39Improved
Use layer-progressive fusion instead of cross-attention in all layers (ablation)Ours · MEADemotion accuracy (%): 69.44 -> 82.05Improved
Use layer-progressive fusion instead of cross-attention in all layers (ablation)Ours · MEADLSE-C: 4.34 -> 7.52Improved
Ten-step flow-matching sampler with motion dictionary instead of 40-step diffusion (Hallo)Ours · inference speedFPS: 0.55 -> 91.23Improved
Ours vs diffusion baselines on emotion accuracyOurs vs Hallo/EchoMimic/Sonic/FLOAT · RAVDESSemotion accuracy (%): 45.00 (best baseline FLOAT) -> 62.50Improved
Ours vs baselines on LSE-C lip-sync confidenceOurs · MEADLSE-C: 7.92 vs EAT 7.76, EDTalk 7.95, Sonic 8.09Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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