Metraipolis › archive › dc_fd2931da27ee
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models — arXiv:2608.11174
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11174
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:36:21.026Z
- SHA-256 of the archived text
d460836d44f014a083c4cf18d3646cb989092c0049fe4600fc8db98dd873514b- Stable URL of this page
https://metraipolis.com/documento/dc_fd2931da27ee
How to cite
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models — arXiv:2608.11174 — arXiv (en), https://arxiv.org/abs/2608.11174 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd2931da27ee (Metraipolis archive dc_fd2931da27ee, sha256 d460836d44f014a083c4cf18d3646cb989092c0049fe4600fc8db98dd873514b)
BibTeX
@misc{dcfd2931da27ee,
title = {VIScore: Diagnosing Planning-Relevant Quality in Latent World Models — arXiv:2608.11174},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11174},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd2931da27ee; sha256 d460836d44f014a083c4cf18d3646cb989092c0049fe4600fc8db98dd873514b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11174. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Regulating the latent space to an isotropic Gaussian distribution provides a stable and information-maximized landscape for world model planning. However, the latent space property and successful planning remain disconnected. We first study this by comparing SIGReg and VISReg, two regularization loss functions with the same distribution target but different properties. Compared with SIGReg, VISReg has more flexibility in controlling the weights of center, scale, and shape regularization, and a larger batch size brings a finer distribution approximation. We find that the former, despite being beneficial in self-supervised learning (SSL), does not help the planning, whereas the latter improves the planning success on out-of-domain (OOD) datasets. This motivates a deep understanding of the factors that correlate with the success rate. Unlike the previous metrics focusing on the encoded latent only, we propose the Veracity-Influence-Sobriety score (VIScore), a metric that quantifies the reachability and capacity of a predictor given the encoded feature, and the hallucination of the searching-based planner. Compared with straightness, physical-state probing, and empowerment, we show that, with the measurement covering encoder, predictor, and planner, VIScore explains the success rate better than the others, as reflected by a strong Spearman correlation. Specifically, VIScore consistently achieves a Spearman correlation over 0.75 on both seen and unseen models and datasets on the cross-task success rate pool. Moreover, VIScore is the only metric that has a calibration error below the constant fit across all testing scenarios, showcasing the importance of these three aspects in planning success. We hope this metric can help future studies on world model design and diagnosis. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.11174 — 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 2026-10-19T06:27:16.727Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).