This paper introduces Graph World Models (GWMs) as a unified research paradigm, addressing the limitations of classical world models through structured graph representations. It proposes a novel taxonomy for GWMs based on relational inductive biases (spatial, physical, and logical) and discusses future research directions.

This paper introduces a novel neural network framework that combines a discrete noise graph diffusion model with an autoregressive solver to enhance solutions for Vehicle Routing Problems (VRPs). By learning and integrating problem constraints through a generated constraint matrix, the approach improves robustness and achieves state-of-the-art performance on various benchmarks.

This paper introduces CogniSNN, a novel Spiking Neural Network (SNN) paradigm that incorporates Random Graph Architectures (RGA) to address the limitations of traditional, rigid SNN designs. CogniSNN enhances neuron-expandability, pathway-reusability, and dynamic-configurability, leading to improved performance, robustness, and continual learning capabilities in multi-task scenarios.