Papers
arxiv:2609.30761

Timo: Taming Multimodal Diffusion Transformers for Human Motion Generation

Published on Oct 10
Authors:
,
,
,

Abstract

Timo, a kinematics-aware multimodal diffusion transformer framework, improves human motion generation by combining fully shared bidirectional text-motion attention and flow matching with rotational-kinematics supervision and a two-stage curriculum, outperforming prior methods on a multi-dataset benchmark.

Most existing human motion generation (HMG) methods use cross-attention modules to inject text semantics, but ignore the importance of bidirectional modeling between motion and text tokens, which limits text comprehension. A straightforward idea is introducing multimodal diffusion transformers (MMDiT), which have shown effective joint text--visual modeling in vision generation, into HMG. However, we find that articulated motion is temporally coherent but weakly correlated across joints, in which directly applying an MMDiT with flow matching produces poorly coordinated and jerky motion. In this work, we propose Timo, a novel kinematics-aware MMDiT framework tailored for HMG. Timo combines fully shared multimodal attention for bidirectional text--motion modeling with flow matching, geometric and rotational-kinematics supervision that compares actual rotations and their changes over time, and a two-stage curriculum progressing from broad motion learning to detailed caption alignment. Further, we construct a benchmark of 40{,}025 held-out clips from six public datasets spanning diverse actions, assessing six complementary dimensions under a common evaluator and scoring protocol. Our model substantially outperforms state-of-the-art methods in both quantitative and qualitative evaluations. Remarkably, Timo surpasses Kimodo on five of six dimensions, achieving a 40.8% relative improvement in the average benchmark score. Project page: https://kyfafyd.wang/projects/timo. Demo page: https://timo.kyfafyd.wang.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.30761
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.30761 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.30761 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.