Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation

ArXi:2603.15759v1 Announce Type: cross Simulation-to-real transfer remains a central challenge in robotics, as mismatches between simulated and real-world dynamics often lead to failures. While reinforcement learning offers a principled mechanism for adaptation, existing sim-to-real finetuning methods struggle with exploration and long-horizon credit assignment in the low-data regimes typical of real-world robotics. We