Tag
This paper introduces a bidirectional latent diffusion model that steps dynamical systems forward or backward in time, using round-trip consistency as a self-supervised test-time error signal to predict rollout errors without ground truth or ensembles.
This paper analyzes long-horizon rollout error in Graph World Models (GWMs), proposing a unified framework with dynamic edges and introducing Error-Aware GWM that uses spectral regularization, rollout consistency, and critical-node weighting to prevent divergence.