Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models

Excerpt

arXiv:2608.15156v1 Announce Type: cross Abstract: World models may predict the future without making clear which parts of their hidden state actually drive those predictions. We ask whether a small, directly addressable hidden-state change can place a learned world model on the intended counterfactual trajectory and then let the model continue that future on its own. We study a recurrent world model with a 192-dimensional hidden state in a controlled two-object, two-dimensional collision environ