Skip to main content
Search

# MixReact

1 related articles

Subscribe to updates
  1. arXiv

    Humanoid agents no longer react only to motion trajectories: MixReact unifies text, audio and video cues in a physics-simulation loop

    Humanoid reaction generation has mostly conditioned on a partner's 3D motion trajectory and stayed purely kinematic, leaving artifacts such as ground penetration, foot sliding and floating. MixReact maps text, audio and video cues into a shared semantic memory, lets a discrete branch pick a whole reaction and a continuous branch predict states window by window, and executes it in closed loop through a history-aware action Transformer in physics simulation. On the video-cue ViMo set it lowers FID by 17.5% and skating error by 34.2% relative to NOUS++, and under audio cues it cuts floating error by 40.9% relative to ReactMotion++.

You’re all caught up