Metraipolis › archive › dc_e5d603756ebb

MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching — arXiv:2610.02260

Source
arXiv
Original
https://arxiv.org/abs/2610.02260
License (as archived)
CC0-1.0
Archived
2026-10-05T22:48:52.119Z
SHA-256 of the archived text
e8f8e0723a78931b1e7647278a028e1d9119db776c1ce9631c6263e5c41bdbe6
Stable URL of this page
https://metraipolis.com/documento/dc_e5d603756ebb

How to cite

MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching — arXiv:2610.02260 — arXiv, https://arxiv.org/abs/2610.02260 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e5d603756ebb (Metraipolis archive dc_e5d603756ebb, sha256 e8f8e0723a78931b1e7647278a028e1d9119db776c1ce9631c6263e5c41bdbe6)
BibTeX
@misc{dce5d603756ebb,
  title = {MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching — arXiv:2610.02260},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02260},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e5d603756ebb; sha256 e8f8e0723a78931b1e7647278a028e1d9119db776c1ce9631c6263e5c41bdbe6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02260. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws. However, existing constrained samplers often face a trade-off: \textit{enforcing constraints can substantially displace samples from the pretrained data distribution}. To address this trade-off, we introduce \textbf{MintFlow}, a training-free constrained sampling framework that formulates constraint enforcement as a minimal intervention on the pretrained flow trajectory. MintFlow seeks the minimal perturbation of an intermediate flow state such that its subsequent evolution under the pretrained flow field satisfies the target constraint. By minimally perturbing the flow state while keeping the pretrained flow field unchanged, MintFlow enforces the constraint while minimizing unnecessary deviation from the pretrained distribution. An adjoint formulation yields a closed-form expression for this perturbation, eliminating expensive iterative optimization. Furthermore, MintFlow adaptively selects the intervention time to balance the required perturbation magnitude with its amplification by the remaining flow. Across a range of tasks in generative vision and physical system modeling, MintFlow achieves competitive constraint satisfaction while preserving the pretrained generative distribution substantially better than state-of-the-art constrained methods.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02260 — 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 2026-10-05T22:45:55.568Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).