NVIDIA Releases ARDY: Real-Time Interactive Human Motion Generation Model
rsasaki0109 · x · 2026-08-27
NVIDIA has released ARDY, an autoregressive diffusion model designed for interactive human motion generation (SIGGRAPH 2026). ARDY supports online text prompting and flexible long-horizon kinematic constraints—such as root paths, waypoints, full-body keyframes, and sparse joint positions/rotations—with real-time responsiveness. The GitHub repository provides code, checkpoints, and demos for the pre-trained models.
More from Multimodal
- Old FPV Drone Video Rebuilt Into Stunning 3D via Lichtfeld Studio's Gaussian Splatting — janusch_patas · 2026-08-27
- Fal model generates long clips in 15 seconds, a transformative speed — JenniferHli · 2026-08-27
- FIRM-Video: Reliable Reward Models via Checklist Verification — VisionXLab · 2026-08-27
- Surflo: Generate Consistent 3D Surfaces from Arbitrary Photos — jonstephens85 · 2026-08-27
- Meitu MT Lab Presents CFT for Stable Portrait Relighting at ECCV 2026 — jiqizhixin · 2026-08-27
- 15-Second 768p Video Generated in 5.12 Seconds — umesh_ai · 2026-08-27