Loading
Life sciences · Preprint
arXiv · September 4, 2026
Posted before peer review. The findings may change or fail to hold.
UniMate is an unpublished machine learning model for automatic motion synthesis across diverse skeletal topologies, trained on a curated dataset of over 13,000 motion sequences. The work is a technical preprint in computer graphics and vision, not a clinical or biomedical study, and does not report evidence relevant to medical practice or health outcomes.
Preprint.
Dataset (UniML3D) comprises 13,006 motion sequences spanning seven skeleton categories (bipedal, quadrupedal, avian, marine, insectoid, serpentine, articulated rigid objects) Model supports zero-shot cross-topology transfer, in-betweening, expansion, and text-guided editing Outperforms state-of-the-art baselines in quality, generalization, and efficiency (specific metrics not provided in abstract)
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unrefereed machine learning preprint describing a novel model architecture and dataset for motion synthesis; it reports no clinical outcomes, human trials, or peer-reviewed validation.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference. We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a topology-aware diffusion transformer, which integrates skeletal topology into attention via three mechanisms: (1) a graph-aware attention bias from pairwise joint relations and geodesic distances; (2) a spectral rotary position embedding generalizing RoPE to arbitrary kinematic trees via the graph Laplacian; and (3) a global topological conditioner attention-pooled from the rest-pose skeleton. We also curate UniML3D, 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid objects with unified canonicalization and text pairing. Trained on this dataset, UniMate outperforms state-of-the-art baselines in quality, generalization, and efficiency, and supports zero-shot cross-topology transfer, in-betweening, expansion, and text-guided editing. Our project page is available at https://linzhanmou.com/unimate/.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.