Twin Rollouts: Noise-Coupled Counterfactual Branching in Interactive Video World Models

2026-08-09

AI Summary

This work addresses the challenge of effectively modeling counterfactual outcomes following action interventions in interactive video world models. The authors propose a noise-coupled dual-branch unrolling mechanism that, building upon a shared state prefix and exogenous noise, bifurcates only the action stream after the intervention point to enable precise counterfactual generation. By explicitly recovering exogenous noise from self-generated trajectories, the method circumvents the traditional difficulties of approximate inversion and reformulates the principle of minimal change into a verifiable spatiotemporal locality metric. Grounded in Pearl’s causal framework, the approach integrates state branching, noise coupling, and computable causal descendant regions to construct a discriminator-free counterfactual evaluation system, thereby providing reinforcement learning with reliable reward signals.

Abstract

Interactive video world models generate rollouts autoregressively under an action stream, yet they are trained and evaluated almost exclusively on factual prediction. We study counterfactual generation inside the rollout: given a trajectory the model has itself generated, what would have happened had the actions differed from step t* onward? We formalize noise-coupled twin rollouts --- a factual and a counterfactual branch sharing the generated prefix and the future exogenous noise sequence, diverging only in the action stream at an intervention point. Because the factual branch is self-generated, its exogenous noise is known exactly: the abduction step of Pearl's counterfactual procedure is exact by construction, sidestepping the approximate-inversion problem faced by editing-based pipelines. Noise coupling further turns the minimal-change principle into a per-sample verifiable property: we define a spatiotemporal locality metric that penalizes divergence outside the causal descendants of the intervention, computable against simulator ground truth without a learned judge. Forking the simulator state at t* yields ground-truth counterfactual re-renders, which we use as verifiable rewards for post-training. This note establishes the formal framework, metric definitions, and positioning; experiments are forthcoming.

Problem

• counterfactual generation
• interactive video world models
• noise coupling
• twin rollouts
• causal intervention

Innovation

• counterfactual generation
• twin rollouts
• noise coupling
• interactive video world models
• causal intervention