Metraipolis › archive › dc_8728efac06b1
Flow-Guided Target-Space Alignment via Path Consistency — arXiv:2611.09863
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09863
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:34:19.587Z
- SHA-256 of the archived text
cd5947657d93a66afa4414e385f838de64897dd9b4cf11946917d4ed03ff36f7- Stable URL of this page
https://metraipolis.com/documento/dc_8728efac06b1
How to cite
Flow-Guided Target-Space Alignment via Path Consistency — arXiv:2611.09863 — arXiv (en), https://arxiv.org/abs/2611.09863 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8728efac06b1 (Metraipolis archive dc_8728efac06b1, sha256 cd5947657d93a66afa4414e385f838de64897dd9b4cf11946917d4ed03ff36f7)
BibTeX
@misc{dc8728efac06b1,
title = {Flow-Guided Target-Space Alignment via Path Consistency — arXiv:2611.09863},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09863},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8728efac06b1; sha256 cd5947657d93a66afa4414e385f838de64897dd9b4cf11946917d4ed03ff36f7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09863. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many multimodal alignment problems require mapping a source modality into a fixed space defined by a target modality, where the target space is not merely an intermediate embedding but is used directly for downstream analysis. In this setting, successful alignment should preserve both the global structure of the target distribution and the instance-level correspondence observed in paired source--target training data. Existing objectives typically address only part of this goal: contrastive losses encourage relative similarity, distribution-matching losses improve marginal agreement, and pointwise regression fits each source sample to its paired target without explicitly modeling target-space path geometry. We propose FlowAlign, a flow-guided target-space alignment method that repurposes conditional flow matching as a training-time alignment signal rather than an inference-time transport model. FlowAlign uses the learned flow field to guide the alignment of source-side representations with the fixed target space, encouraging them to preserve paired correspondence while remaining compatible with the global target-space structure. We further provide theoretical analysis showing how FlowAlign helps improve paired correspondence by controlling endpoint accuracy and capturing local target-space geometry. Experiments on synthetic data, paired single-cell multiome benchmarks, and image--text alignment demonstrate that FlowAlign improves instance level correspondence while preserving target-space structure across different modality settings. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.09863 — 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 2026-11-09T22:30:47.295Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).