pith. sign in

To maintain an information capacity comparable to our continuous baseline, we configure the VQ layer with a codebook size of 8 and a quantized embedding dimension of

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

DiLA: Disentangled Latent Action World Models

cs.CV · 2026-05-15 · unverdicted · novelty 6.0

DiLA uses content-structure disentanglement driven by predictive bottlenecks to create semantically structured latent actions for high-fidelity video world models.

citing papers explorer

Showing 1 of 1 citing paper.

  • DiLA: Disentangled Latent Action World Models cs.CV · 2026-05-15 · unverdicted · none · ref 30

    DiLA uses content-structure disentanglement driven by predictive bottlenecks to create semantically structured latent actions for high-fidelity video world models.