Flow-Guided Target-Space Alignment via Path Consistency
[Sztuczna inteligencja] Autorzy: Ruizhi Yuan, Zeqiu Yu, Wei Gao i 3 więcej
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…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja