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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Yannan, Tiwari, Garvita, Zhang, Xiaohan, Bora, Pankaj, Birdal, Tolga, Lenssen, Jan Eric, Pons-Moll, Gerard
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917362716901376
author He, Yannan
Tiwari, Garvita
Zhang, Xiaohan
Bora, Pankaj
Birdal, Tolga
Lenssen, Jan Eric
Pons-Moll, Gerard
author_facet He, Yannan
Tiwari, Garvita
Zhang, Xiaohan
Bora, Pankaj
Birdal, Tolga
Lenssen, Jan Eric
Pons-Moll, Gerard
contents We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or auto-regressively over multiple latents. In this paper, we study how to make diffusion on continuous motion latents work best. We focus on two questions: (1) how to build a semantically aligned latent space so diffusion becomes more effective, and (2) how to best inject text conditioning so the motion follows the description closely. We propose a semantic-aligned motion encoder trained with frame-level text labels so that latents with similar text meaning stay close, which makes the latent space more diffusion-friendly. We also compare single-token conditioning with a multi-token cross-attention scheme and find that cross-attention gives better motion realism and text-motion alignment. With semantically aligned latents, auto-regressive generation, and cross-attention text conditioning, our model sets a new state of the art in human motion generation on standard metrics and in a user study. We will release our code and models for further research and downstream usage.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13840
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoLingo: Motion-Language Alignment for Text-to-Motion Generation
He, Yannan
Tiwari, Garvita
Zhang, Xiaohan
Bora, Pankaj
Birdal, Tolga
Lenssen, Jan Eric
Pons-Moll, Gerard
Computer Vision and Pattern Recognition
We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or auto-regressively over multiple latents. In this paper, we study how to make diffusion on continuous motion latents work best. We focus on two questions: (1) how to build a semantically aligned latent space so diffusion becomes more effective, and (2) how to best inject text conditioning so the motion follows the description closely. We propose a semantic-aligned motion encoder trained with frame-level text labels so that latents with similar text meaning stay close, which makes the latent space more diffusion-friendly. We also compare single-token conditioning with a multi-token cross-attention scheme and find that cross-attention gives better motion realism and text-motion alignment. With semantically aligned latents, auto-regressive generation, and cross-attention text conditioning, our model sets a new state of the art in human motion generation on standard metrics and in a user study. We will release our code and models for further research and downstream usage.
title MoLingo: Motion-Language Alignment for Text-to-Motion Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.13840