57
60
60
60
30
30
60
45
57
35
35
30
35
60
55
60
57
57
30
57
60
30
57
UniMate: One Unified Model to Animate Diverse Skeletons
Researchers introduce UniMate, a topology-aware diffusion transformer generating text-driven motion for arbitrary 3D skeletons without per-skeleton retraining.
UniMate is 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 fine-tuning. It uses a topology-aware diffusion transformer combining graph-aware attention bias, a spectral rotary position embedding generalizing RoPE via the graph Laplacian, and a rest-pose topological conditioner. Trained on UniML3D, a curated set of 13,006 motion sequences spanning bipedal to serpentine skeletons, it outperforms state-of-the-art baselines and supports zero-shot cross-topology transfer, in-betweening, and text-guided editing.
16
30
42
30
60
55
Week in review: Microsoft fixes exploited zero-day, Mirai botnets target unpatched Wazuh servers
60
30
60
42
45
42
60
30
60
60
30