SOICT 2026 · Under Review

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

Hung Dinh1, Binh Mai1, Tran Quoc Bao Le1, Lam Nguyen1, Cong Tran1†
1 Posts and Telecommunications Institute of Technology, Vietnam
† Corresponding author

Abstract

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 \(89.2\times\) speedup.

Method Overview

A frozen multi-step teacher is used offline to construct a multi-candidate motion bank for each text prompt, while the one-step student generates a set of motion candidates from independently sampled noise. Training aligns the two sets using asymmetric bidirectional matching in both representation and decoded motion spaces, with gradients propagated only through the student.

Overview of the MixiMotion distillation framework
Figure 1: Overview of MixiMotion. A frozen multi-step teacher generates \(K\) motion candidates per prompt to construct an offline teacher bank, while the one-step student generates \(M\) candidates from independent noise samples. The teacher and student sets are aligned using asymmetric bidirectional matching in the normalized representation and differentiably decoded motion spaces. Only the student is optimized during training.

Motion Samples

Randomly sampled evaluation clips under a shared renderer, camera, and lighting. Not selected by output quality.

HY-Motion-1.0-Lite (50 NFE)
→
MixiMotion (1 NFE) · “A person walks forward.”
HY-Motion-1.0-Lite (50 NFE)
→
MixiMotion (1 NFE) · “A person shoots a basketball.”
HY-Motion-1.0-Lite (50 NFE)
→
MixiMotion (1 NFE) · “A person waves.”
Qualitative comparison of HY-Motion-1.0-Lite and MixiMotion
Figure 2: Qualitative comparison on three randomly sampled evaluation instructions. HY-Motion-1.0-Lite (upper row) and MixiMotion (lower row) use the same renderer, camera, and lighting. The examples are sampled without manual selection based on generation quality.

Comparison with Baselines

Compare MixiMotion with compact one- and few-step baselines on the same prompts. Cross-family clips keep native renderers.

Prompt MotionLCM-1 MotionHiFlow MixiMotion (Ours) HY-Motion-1.0-Lite
"A person walks forward."
"A person shoots a basketball."

Experimental Results

ViMoGen Semantic Alignment

Question-level correctness on ViMoGen. Overall pools all judgments across 2{,}000 prompts rather than averaging category scores. MixiMotion versus the 50-NFE HY-Motion-1.0-Lite teacher is renderer-controlled.

Method NFE ↓ Daily ↑ Fit. ↑ Game ↑ Loco. ↑ Social ↑ Sports ↑ Overall ↑
One-step methods
MixiMotion (Ours) 1 0.842 0.721 0.886 0.944 0.903 0.806 0.835
MotionLCM-1 1 0.801 0.709 0.881 0.951 0.911 0.772 0.825
Naive 1-step teacher 1 0.681 0.604 0.743 0.823 0.768 0.642 0.711
Multi-step methods
HY-Motion-1.0-Lite (teacher) 50 0.874 0.738 0.901 0.958 0.918 0.823 0.858
MLD 50 0.811 0.708 0.896 0.958 0.931 0.780 0.840
MDM 50 0.820 0.724 0.865 0.950 0.927 0.752 0.833
MotionDiffuse 1000 0.782 0.689 0.855 0.926 0.899 0.742 0.809

MixiMotion is best among one-step methods (0.835 vs 0.825 MotionLCM-1 and 0.711 naive 1-step). It remains 2.3 points below the 50-step teacher (0.858).

Efficiency (RTX 5090, BF16)

Method Params (M) ↓ NFE ↓ Gen. ms ↓ E2E ms ↓
HY-Motion-1.0-Lite 460.0 50 829.58 968.25
MixiMotion (Ours) 460.0 1 9.30 143.55
MotionHiFlow 33.1 14 77.32 83.80
MotionLCM-1 26.5 1 3.04 13.94

The \(89.2\times\) generation speedup is versus the 50-NFE HY-Motion-1.0-Lite teacher (\(829.58\) ms \(\rightarrow\) \(9.30\) ms). MotionLCM-1 remains smaller and faster.

Limitations and Future Work

Limitations

MixiMotion reuses the teacher backbone, so this is not an architecture result. All systems generate fixed 120-frame clips. Semantic score is 0.835 versus 0.858 for the 50-step teacher; human overall is 4.33 versus 4.50. Nearest-neighbor set matching does not recover the teacher distribution. Variable-length generation is untested.

Future Work

Independently sourced prompts, a common cross-family renderer, and variable-length generation would test whether the one-step quality–latency trade-off generalizes beyond this teacher family.

Citation

@inproceedings{dinh2026miximotion,
  title={MixiMotion: One-Step Text-to-Motion Generation via Asymmetric Set Distillation},
  author={Hung Dinh and Binh Mai and Tran Quoc Bao Le and Lam Nguyen and Cong Tran},
  booktitle={SOICT},
  year={2026}
}