Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated Jul 21 • 160
Physical AI Collection Collection of open, commercial-grade datasets for physical AI developers • 23 items • Updated 8 days ago • 94
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models Paper • 2502.06608 • Published Feb 10 • 40
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models Paper • 2502.02492 • Published Feb 4 • 66