SOURCE-LINKED INTELLIGENCE

Flexible Motion Generation from Language and Style References

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

We introduce FlexMoGen, a novel framework for flexible human motion synthesis conditioned on both natural language descriptions and motion style references. Text prompts are effective at defining semantic content, but they are often limited in capturing fine-grained style details such as timing, limb articulation, and expressive dynamics. A style example clip supplements the text by conveying these nuanced motion characteristics directly, enabling the model to preserve high-level intent while reproducing the desired stylistic traits. Given a text prompt and a style example clip, FlexMoGen gene

Read original source ↗ Open in workspace

recordType

paper

region

Global