Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated May 21 • 150
Physical AI Collection Collection of commercial-grade datasets for physical AI developers • 22 items • Updated 10 days ago • 63
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models Paper • 2502.06608 • Published Feb 10 • 41
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models Paper • 2502.02492 • Published Feb 4 • 67