Metraipolis › archive › dc_38dbabf30e52
Logical Guidance of Stochastic Interpolants — arXiv:2610.38648
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38648
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:24:50.581Z
- SHA-256 of the archived text
7733cc59bbf3e144c1b3acd1c8f5473e068a4dcb2af19f76e4c54236b4b6d5e9- Stable URL of this page
https://metraipolis.com/documento/dc_38dbabf30e52
How to cite
Logical Guidance of Stochastic Interpolants — arXiv:2610.38648 — arXiv (en), https://arxiv.org/abs/2610.38648 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_38dbabf30e52 (Metraipolis archive dc_38dbabf30e52, sha256 7733cc59bbf3e144c1b3acd1c8f5473e068a4dcb2af19f76e4c54236b4b6d5e9)
BibTeX
@misc{dc38dbabf30e52,
title = {Logical Guidance of Stochastic Interpolants — arXiv:2610.38648},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38648},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_38dbabf30e52; sha256 7733cc59bbf3e144c1b3acd1c8f5473e068a4dcb2af19f76e4c54236b4b6d5e9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38648. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Guidance and composition of generative models have applications in visual design, chemistry, and biology. Logical guidance composes conditional scores exactly for diffusion models. However, Flow Matching (FM) and Stochastic Interpolants (SI) learn velocity fields. We show that negation and exclusive disjunction admit exact conditional velocity composition on any interpolant, whereas conjunction, and therefore any formula containing one, is exact on Gaussian paths but in general incurs a drift-interaction error, so composed velocities need not sample the logical target. LOGSI solves this by using score-based re-equilibration as our principled mechanism and falling back to the Gaussian-path velocity rule as an approximate transport predictor. In non-Gaussian bridge problems, generation alternates transport steps with score re-equilibration steps. On image trans fer (EMNIST to CMNIST, CelebA) and QM9 source-to-target molecular editing with logical attribute constraints, LOGSI improves rule conformity at the same network-evaluation budget over composed-velocity baselines, while also improving fidelity on the image tasks. More broadly, LOGSI applies wherever stochastic interpolants need guidance and logical combinations of constraints are natural. 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/2610.38648 — 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 2026-11-01T02:12:44.129Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).