Higher Gauge Flow Models
This work addresses a domain-specific problem for researchers in generative modeling, offering an incremental advancement over existing Gauge Flow Models.
The paper tackles the problem of enhancing Generative Flow Models by introducing Higher Gauge Flow Models, which use an L∞-algebra to incorporate higher geometry and symmetries, resulting in substantial performance improvements on a Gaussian Mixture Model dataset.
This paper introduces Higher Gauge Flow Models, a novel class of Generative Flow Models. Building upon ordinary Gauge Flow Models (arXiv:2507.13414), these Higher Gauge Flow Models leverage an L$_{\infty}$-algebra, effectively extending the Lie Algebra. This expansion allows for the integration of the higher geometry and higher symmetries associated with higher groups into the framework of Generative Flow Models. Experimental evaluation on a Gaussian Mixture Model dataset revealed substantial performance improvements compared to traditional Flow Models.