Metraipolis › archive › dc_2fb30d9ff7ad

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation — arXiv:2610.00686

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00686
License (as archived)
CC0-1.0
Archived
2026-10-06T19:11:28.195Z
SHA-256 of the archived text
4daf7b0893ac17725d4b067388468677d47be060d78af540485a08a2d7807879
Stable URL of this page
https://metraipolis.com/documento/dc_2fb30d9ff7ad

How to cite

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation — arXiv:2610.00686 — arXiv (en), https://arxiv.org/abs/2610.00686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fb30d9ff7ad (Metraipolis archive dc_2fb30d9ff7ad, sha256 4daf7b0893ac17725d4b067388468677d47be060d78af540485a08a2d7807879)
BibTeX
@misc{dc2fb30d9ff7ad,
  title = {SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation — arXiv:2610.00686},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fb30d9ff7ad; sha256 4daf7b0893ac17725d4b067388468677d47be060d78af540485a08a2d7807879},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for the optimal performance of each of these, both in terms of fidelity and semantics. Flexible-length, coarse-to-fine tokenizers yield exactly that: the first coarse tokens carry the clip's global semantics while later tokens further specify details. Existing flexible tokenizers only apply a representation-alignment (REPA) loss on early decoder hidden states, a target the decoder can partly meet from its noised input instead. We introduce SemanTok, a flexible video tokenizer that feeds frozen DINO features into its encoder and adds lightweight heads that reconstruct them from each retained token prefix alone. SemanTok achieves high semantic alignment and video fidelity at every AR model size: a 201M SemanTok AR model matches or beats a VideoFlexTok AR model $3.4\times$ its size, and larger SemanTok AR models further improve fidelity. It keeps semantic alignment on out-of-distribution classes and gives the decoder higher semantic alignment at every noise level, including pure noise. It performs well in both reconstruction and generation, and its short token prefixes are cheaper to predict and give better generation fidelity, with pixel detail deferred to later tokens.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.00686 — 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 2026-10-06T17:37:36.688Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).