Metraipolis › archive › dc_85cffb05985b
Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models — arXiv:2611.04028
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04028
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:02:57.913Z
- SHA-256 of the archived text
92cb7683666a93a9607d269305cbbc8cb46fd2859c09683aa6e4aa31220a8e3f- Stable URL of this page
https://metraipolis.com/documento/dc_85cffb05985b
How to cite
Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models — arXiv:2611.04028 — arXiv (en), https://arxiv.org/abs/2611.04028 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85cffb05985b (Metraipolis archive dc_85cffb05985b, sha256 92cb7683666a93a9607d269305cbbc8cb46fd2859c09683aa6e4aa31220a8e3f)
BibTeX
@misc{dc85cffb05985b,
title = {Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models — arXiv:2611.04028},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04028},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85cffb05985b; sha256 92cb7683666a93a9607d269305cbbc8cb46fd2859c09683aa6e4aa31220a8e3f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04028. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Effective world modeling requires compressing salient history information that facilitates future prediction. However, most existing approaches inherit tokenization and conditioning mechanisms from video generation, where objectives are centered around perceptual realism rather than predictive utility. This discrepancy limits the world model's effectiveness, especially in environments dominated by visual nuisances or task-irrelevant background details. To this end, we introduce Compression Forcing (CF), a general framework that aligns history compression with the predictive objective of world modeling. Compression Forcing features Dynamics-Aware Tokenization (DAT), a novel tokenization method that compresses history observations into a sequence ordered by decreasing dynamics saliency. Built on a diffusion backbone, this structure enables Hierarchical History Guidance (HG-H), allowing selective amplification of dynamics-salient information during inference. Extensive experiments across various environments demonstrate improved prediction fidelity, physical realism, and downstream decision-making performance, establishing Compression Forcing as a highly flexible and effective approach for world modeling. 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/2611.04028 — 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 2026-11-04T18:39:37.451Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).