pith. sign in

Deco-vae: Learning compact latents for video reconstruction via decoupled representation

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

Video Generation with Predictive Latents

cs.CV · 2026-05-04 · unverdicted · novelty 5.0

PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.

citing papers explorer

Showing 1 of 1 citing paper.

  • Video Generation with Predictive Latents cs.CV · 2026-05-04 · unverdicted · none · ref 61

    PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.