AI Paper Atlas

Research map / Video / Video generation

MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation

Yannan He, Garvita Tiwari, Xiaohan Zhang, Pankaj Bora, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll

CVPR 2026 · Video › Video generation · approach: Text-to-motion diffusion · 6 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
replace CLIP with T5 text encoder in single-token AdaLN conditioning (ablation)MARDM-style AE model · HumanML3D (MARDM-67)FID: 0.114 -> 0.077Improved
add multi-token cross-attention conditioning instead of single-token AdaLN (ablation)T5 + AE · HumanML3D (MARDM-67)FID: 0.077 -> 0.051Improved
add multi-token cross-attention conditioning instead of single-token AdaLN (ablation)T5 + AE · HumanML3D (MARDM-67)R-Precision Top-1: 0.508 -> 0.533Improved
use semantically aligned autoencoder (SAE) instead of vanilla AE (ablation)CrossAttn + T5 · HumanML3D (MARDM-67)R-Precision Top-1: 0.533 -> 0.544Improved
use semantically aligned autoencoder (SAE) instead of vanilla AE (ablation)CrossAttn + T5 · HumanML3D (MARDM-67)FID: 0.051 -> 0.066Hurt
use cosine semantic loss instead of InfoNCE (ablation)SAE · HumanML3D (MARDM-67)FID: 0.129 -> 0.062Improved
lower semantic loss weight lambda_sem from 0.1 to 0.001 (ablation)SAE with cosine and KL · HumanML3D (MARDM-67)FID: 0.071 -> 0.066Improved
add KL divergence to SAE training (lambda_sem 0.001) (ablation)SAE with cosine · HumanML3D (MARDM-67)FID / R-Precision Top-1: FID 0.062 -> 0.066; Top-1 0.535 -> 0.544Mixed
add a 6-layer text adapter before cross-attention (ablation)MoLingo (VAE) · HumanML3D (MARDM-67)FID: 0.057 -> 0.049Improved
use a 3-layer text adapter instead of none (ablation)MoLingo (VAE) · HumanML3D (MARDM-67)FID: 0.057 -> 0.060Hurt
add repetitive class-token filtering during SAE training (ablation)MoLingo (SAE) · HumanML3D (MARDM-67)FID: 0.096 -> 0.066Improved
add repetitive class-token filtering during SAE training (ablation)MoLingo (SAE) · HumanML3D (MARDM-67)R-Precision Top-1: 0.524 -> 0.544Improved

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