Graphs are invariant under node permutations, motivating permutation-equivariant architectures in generative models. In flow matching, however, symmetry also affects the source-target coupling: one must choose both which graphs to pair and which node representatives to align. We study these two forms of alignment, term...
Evaluating text generation requires measuring how well the generated distribution matches the data distribution. For autoregressive models, this is done by the perplexity. Diffusion and flow-based language models can only provide a likelihood bound, whose tightness differs between model families. Sample-based substitut...
Gregor Kornhardt, Moritz Piening, J. Chemseddine et al.· 0 citations
This work develops this perspective theoretically, showing that quotient couplings can be lifted to aligned representatives without additional cost and that symmetrization yields equivariant flow-matching minimizers, including for categorical endpoint prediction.
Moritz Piening, C. Wald· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.