{"ID":2884612,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06096","arxiv_id":"2508.06096","title":"Bounding Distributional Shifts in World Modeling through Novelty Detection","abstract":"Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of the action and state space during training to prevent divergence during inference. To make a model-based planning algorithm more robust to the quality of the learned world model, we propose in this work to use a variational autoencoder as a novelty detector to ensure that proposed action trajectories during planning do not cause the learned model to deviate from the training data distribution. To evaluate the effectiveness of this approach, a series of experiments in challenging simulated robot environments was carried out, with the proposed method incorporated into a model-predictive control policy loop extending the DINO-WM architecture. The results clearly show that the proposed method improves over state-of-the-art solutions in terms of data efficiency.","short_abstract":"Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of the action and state space during training to prevent divergence during inferenc...","url_abs":"https://arxiv.org/abs/2508.06096","url_pdf":"https://arxiv.org/pdf/2508.06096v1","authors":"[\"Eric Jing\",\"Abdeslam Boularias\"]","published":"2025-08-08T07:42:14Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false}