AI Paper Atlas

Research map / Video / Video generation

Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Liyang Chen, Tianxiang Ma, Jiawei Liu, Bingchuan Li, Zhuowei Chen, Lijie Liu, Xu He, Gen Li, Qian He, Zhiyong Wu

AAAI 2026 · Video › Video generation · approach: Diffusion-based human image animation · 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
confine finetuning to self-attention layers instead of full finetuning (ablation)HuMo-17B · MoChaAES: 0.529 -> 0.589Improved
confine finetuning to self-attention layers instead of full finetuning (ablation)HuMo-17B · MoChaTVA: 6.157 -> 6.508Improved
use progressive two-stage training instead of single-stage joint training (ablation)HuMo-17B · MoChaID-Cur: 0.724 -> 0.747Improved
use progressive training (ablation)HuMo-17B · MoChaAES: 0.541 -> 0.589No clear effect
add face-location prediction (focus-by-predicting) (ablation)HuMo-17B · MoChaSync-C: 5.946 -> 6.252Improved
add face-location prediction (ablation)HuMo-17B · MoChaID-Cur: 0.730 -> 0.747Improved
add face-location prediction (ablation)HuMo-17B · MoChaTVA: 6.507 -> 6.508No clear effect
scale model from 1.7B to 17BHuMo · In-house subject preservationTVA: 3.222 -> 3.939Improved
HuMo-17B vs OmniHuman-1 on lip syncHuMo-17B · MoChaSync-C: 6.526 vs 6.252Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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