Skip to main content
Search

# Compositional Diffusion

2 related articles

Subscribe to updates
  1. arXiv

    MCDC changes only the initial noise: long-horizon stitching improves on OGBench and stacks with search-based planners

    Compositional diffusion planners split a long-horizon task into short trajectory chunks that are generated separately and stitched, but independently initialized chunks can commit to incompatible local modes, yielding plans that are locally feasible yet globally incoherent. MCDC is a training-free inference method that replaces independent chunk noise with correlated Gaussian noise across neighboring chunks while keeping each chunk's marginal exactly standard Gaussian, biasing the sampler toward compatible overlap modes without touching the pretrained denoiser. On OGBench long-horizon Stitch tasks, MCDC improves consistently over independent sampling at nearly the same inference time and offers a favorable success-cost trade-off against search-based composition.

  2. 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