Papers
1–3 of 3Research Paper·Jan 30, 2026
Adaptive Edge Learning for Density-Aware Graph Generation
Generating realistic graph-structured data is challenging due to discrete structures, variable sizes, and class-specific connectivity patterns that resist conventional generative modelling. While rece...
7.0 viability
Research Paper·Mar 9, 2026
Are Expressive Encoders Necessary for Discrete Graph Generation?
Discrete graph generation has emerged as a powerful paradigm for modeling graph data, often relying on highly expressive neural backbones such as transformers or higher-order architectures. We revisit...
7.0 viability
Research Paper·Mar 11, 2026
Graph-GRPO: Training Graph Flow Models with Reinforcement Learning
Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its su...
7.0 viability