Metraipolis › archive › dc_2ba97cd1bfcf

GRACE: Generation-aware latent compression for efficient video generation — arXiv:2610.10524

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10524
License (as archived): CC0-1.0
Archived: 2026-10-08T12:48:24.623Z
SHA-256 of the archived text: 8adbe1046986ce51d0f695abb8eb206d79004ce6e2da0a4c26ebb2528cda4095
Stable URL of this page: https://metraipolis.com/documento/dc_2ba97cd1bfcf

How to cite

GRACE: Generation-aware latent compression for efficient video generation — arXiv:2610.10524 — arXiv (en), https://arxiv.org/abs/2610.10524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ba97cd1bfcf (Metraipolis archive dc_2ba97cd1bfcf, sha256 8adbe1046986ce51d0f695abb8eb206d79004ce6e2da0a4c26ebb2528cda4095)

BibTeX

@misc{dc2ba97cd1bfcf,
  title = {GRACE: Generation-aware latent compression for efficient video generation — arXiv:2610.10524},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10524},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ba97cd1bfcf; sha256 8adbe1046986ce51d0f695abb8eb206d79004ce6e2da0a4c26ebb2528cda4095},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, since a higher compression ratio degrades reconstruction quality and recovering it requires more channels, which is known to slow the convergence of the DiT. The compressed latent also differs from the one the DiT was trained on, so the pretrained DiT must be either retrained from scratch or adapted at considerable cost. Compressing the autoencoder the DiT was trained with appears to preserve compatibility, yet optimizing it for reconstruction alone still shifts the latent away from the distribution the DiT has learned. To address this, we propose Generation-Aware Latent Compression for Efficient Video Generation (GRACE), a two-stage framework that compresses a pretrained video autoencoder while keeping it compatible with the pretrained DiT. Specifically, we keep a frozen base latent from the pretrained encoder and learn a residual latent for the information lost under stronger compression, while aligning the compressed latent with the pretrained latent in the feature space of the frozen DiT so that the autoencoder is optimized for generation. We then adapt the DiT with lightweight fine-tuning and asymmetric denoising, where the base is denoised ahead of the residual. GRACE reduces the token count of Wan2.1-I2V-14B by 8x and its latency by 11.1x at 480x832x81, while matching the generation quality of the pretrained pipeline before compression on VBench.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.10524 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:15.511Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).