Skip to main content
Search

# CFGComposer

1 related articles

Subscribe to updates
  1. arXiv

    Two frozen experts now compose full-body gestures: CFGComposer restores the dropped cross-modal term, reaching 0.9916 semantic recall

    Generating full-body gestures from speech no longer requires a single joint network trained on scarce tri-modal data. Linearly summing the predictions of separately trained audio-to-motion and text-to-motion diffusion experts implicitly assumes the two conditions are independent given the noisy motion, dropping the cross-modal dependence term. CFGComposer estimates that term with a jointly trained model and injects it at inference as classifier-free guidance; on BEAT it reaches a semantic recall SRGR of 0.9916 and beat alignment BA of 0.1826, against 0.1743 for ground truth.

You’re all caught up