AI★★★★arXiv · 2026-07-09
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
ARDY is a novel interactive human motion generation framework that bridges the gap between offline and online methods. It combines autoregressive diffusion with hybrid representation to enable real-time synthesis with precise control. ARDY can handle complex text semantics and long-horizon goals.
📌 Key points
- ARDY generates realistic 3D human motions in real-time
- Combines autoregressive diffusion with hybrid representation
- Handles complex text semantics and long-horizon goals
本页为 gitzw.com 基于公开来源的 AI 中文解读，非原文转载。