AI Paper Atlas

Research map / Video / Video generation

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

Jing Lin, Ruisi Wang, Junzhe Lu, Ziqi Huang, Guorui Song, Ailing Zeng, Xian Liu, Chen Wei, Wanqi Yin, Qingping SUN, Zhongang Cai, Lei Yang and 1 more

ICLR 2026 · Video › Video generation · approach: World-model video generation

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 adaptive gating between T2M and M2M branches instead of a single branch (ablation)ViMoGen · MBenchMotion Generalizability: 0.54 (T2M only) / 0.59 (M2M only) -> 0.68Improved
add M2M branch conditioned on video motion tokens (M2M only vs video generation baseline) (ablation)ViMoGen · MBenchJitter Degree: 0.0193 -> 0.0145Improved
add T2M-only training on MoCap (vs adaptive) (ablation)ViMoGen · MBenchFoot Sliding: 0.0113 (M2M) -> 0.0039 (T2M)Improved
add synthetic ViGen-derived video data (14k clips) to training (ablation)ViMoGen-light · MBenchMotion Generalizability: 0.50 -> 0.55Improved
add in-the-wild visual MoCap data to training (ablation)ViMoGen-light · MBenchFoot Sliding: 0.0033 -> 0.0042Hurt
add other optical MoCap datasets to HumanML3D (ablation)ViMoGen-light · MBenchMotion Generalizability: 0.44 -> 0.48Improved
use T5-XXL instead of CLIP text encoder (ablation)ViMoGen · MBenchMotion Generalizability: 0.35 -> 0.44Improved
use MLLM text encoder instead of T5-XXL (ablation)ViMoGen · MBenchBody Penetration: 1.05 -> 1.51Hurt
train on descriptive video-style text instead of motion-style text (ablation)ViMoGen · MBenchMotion Generalizability: 0.40 -> 0.48Improved
test with video-style instead of motion-style text after video-style training (ablation)ViMoGen · MBenchMotion Generalizability: 0.48 -> 0.44Hurt
use jointly trained shared-parameter branches instead of VLM-selected MotionLCM/DNO (ablation)ViMoGen · MBenchMotion Generalizability: 0.63 -> 0.68Improved
use intermediate ViGen features as video tokens (ablation)ViMoGen · MBenchconvergence / performanceNo clear effect

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