GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
Graph colouring meets deep learning: Effective graph neural network models for combinatorial problems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CCEM parameterizes compositional energy factors with input-convex neural networks and optimizes over a convex relaxation to enable deterministic scaling from small to large combinatorial reasoning instances.
citing papers explorer
-
Generative Recursive Reasoning
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
-
Convex Compositional Reasoning Models
CCEM parameterizes compositional energy factors with input-convex neural networks and optimizes over a convex relaxation to enable deterministic scaling from small to large combinatorial reasoning instances.