Metraipolis › archive › dc_af293d7fd139
Sparse Planning in Visual World Models via Cost Gradients — arXiv:2610.10274
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10274
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:13.323Z
- SHA-256 of the archived text
50a71e4a7fbe31800c0472715f6c00271acb0b476ba21953b5ec7ddcccef3763- Stable URL of this page
https://metraipolis.com/documento/dc_af293d7fd139
How to cite
Sparse Planning in Visual World Models via Cost Gradients — arXiv:2610.10274 — arXiv (en), https://arxiv.org/abs/2610.10274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af293d7fd139 (Metraipolis archive dc_af293d7fd139, sha256 50a71e4a7fbe31800c0472715f6c00271acb0b476ba21953b5ec7ddcccef3763)
BibTeX
@misc{dcaf293d7fd139,
title = {Sparse Planning in Visual World Models via Cost Gradients — arXiv:2610.10274},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10274},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af293d7fd139; sha256 50a71e4a7fbe31800c0472715f6c00271acb0b476ba21953b5ec7ddcccef3763},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Token-based world models enable fine-grained latent planning, but repeatedly processing large spatial token grids makes action search expensive. We introduce COSTGRAD, a training-free, goal-conditioned selector that ranks spatial tokens by the gradient norm of the planning cost with respect to each input token. By deriving importance from the downstream control objective, COSTGRAD targets tokens that matter for planning rather than merely for prediction. On AdaLN-conditioned predictors at $50\%$ sparsity, COSTGRAD matches or exceeds full-token planning on three of four continuous-control benchmarks, while giving a measured $2.6\times$ wall-clock speedup per environment planning step. Combining token sparsity with reduced CEM search increases this to a $\sim 5\times$ total speedup while still exceeding the full-token baseline. We also identify an architecture-dependent failure mode: in a matched AdaLN-vs-concat comparison, concat maintains comparable full-token performance but pure COSTGRAD loses its advantage over random selection. This difference tracks action-pathway drift: gradient-selected removal produces less drift than random removal on AdaLN, but more on concat. These results highlight selector-architecture compatibility as a design axis for sparse world-model planning. Project page and demos: this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.10274 — 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 2026-10-08T12:14:15.321Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).