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

Source: arXiv cs.RO·2026-08-20 12:00Publish time unverified

arXiv:2608.15156v2 Announce Type: replace 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.