# MixiMotion: One-Step Text-to-Motion Generation via Asymmetric Set Distillation

arXiv: https://arxiv.org/abs/2609.23010 · HTML: https://mlsanity.com/paper/2609.23010/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 26 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation](https://mlsanity.com/paper/2404.04057/) (2024)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [Motion Mamba: Efficient and Long Sequence Motion Generation](https://mlsanity.com/paper/2403.07487/) (2024)
- [Implicit Maximum Likelihood Estimation](https://mlsanity.com/paper/1809.09087/) (2018)
- [StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework](https://mlsanity.com/paper/2405.05691/) (2024)
- [HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation](https://mlsanity.com/paper/2512.23464/) (2025)
- [MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation](https://mlsanity.com/paper/2503.09950/) (2025)
- [MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model](https://mlsanity.com/paper/2501.19083/) (2025)
- [MotionHiFlow: Text-to-motion via hierarchical flow matching](https://mlsanity.com/paper/2604.23264/) (2026)
- [SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation](https://mlsanity.com/paper/2606.31259/) (2026)

## Abstract (arXiv)

Iterative text-to-motion generation delivers high-quality and semantically aligned motions but requires multiple network evaluations, resulting in substantial inference latency. We present MixiMotion, a strict one-step text-to-motion generation framework based on offline set distillation. Instead of distilling a single teacher trajectory for each text prompt, MixiMotion constructs an offline bank of multiple teacher motions and aligns teacher and student sample sets through asymmetric bidirectional matching. The teacher-to-student direction promotes coverage of diverse teacher-supported motions, while the student-to-teacher direction suppresses unsupported generations. We further introduce differentiable decoded-space kinematic supervision to complement normalized representation matching with constraints in the decoded motion space. At inference, MixiMotion generates a complete motion sequence with a single network evaluation, without teacher queries, iterative sampling, or candidate ranking. On ViMoGen, MixiMotion achieves a semantic alignment score of 0.835, outperforming the evaluated one-step baselines and approaching the 0.858 score of its 50-step HY-Motion-1.0-Lite teacher. In blinded human evaluation, MixiMotion obtains an overall rating of 4.33, compared with 4.50 for the teacher, while outperforming the evaluated one-/few-step baselines. Meanwhile, generation latency is reduced from 829.58,ms to 9.30,ms, corresponding to an 89.2× speedup. These results demonstrate an effective quality--efficiency trade-off for strict one-step text-to-motion generation.