Tag: Diffusion Models
NVIDIA Kimodo: AI-Powered 3D Motion Generation
NVIDIA releases Kimodo, a diffusion-based generative model for realistic 3D motion, supporting diverse skeletons including SMPL-X and Unitree G1.
Tencent HunyuanVideo-1.5: Efficient Video Gen
Tencent releases HunyuanVideo-1.5, a compact 8.3B-parameter video generation model with SSTA attention and 1080p super-resolution support.
RND1: Largest Open Diffusion Language Model
Radical Numerics introduces RND1-Base, a 30B parameter diffusion language model converted from autoregressive architecture with 15% efficiency gains.