ARDY is an autoregressive diffusion model designed for interactive motion generation, supporting online text prompting and flexible long-horizon kinematic constraints (root paths/waypoints, full-body ...
The judge-visible surface moves from a dev-machine OpenCV window to a real GUI app on the IVI vECU (SC-1, user-directed) plus an ADA→IVI IPC link — display-track effort grows from ~1 week to 2 weeks ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results