AI RESEARCH
Logic-Guided Vector Fields for Constrained Generative Modeling
arXiv CS.LG
•
ArXi:2602.02009v2 Announce Type: replace Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typically lack mechanisms to enforce declarative constraints at generation time. We propose Logic-Guided Vector Fields (LGVF), a neuro-symbolic framework that injects symbolic knowledge, specified as differentiable relaxations of logical constraints, into flow matching generative models. LGVF couples two complementary mechanisms: (1) a.