{"ID":2833859,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.02473","arxiv_id":"2512.02473","title":"WorldPack: Compressed Memory Improves Spatial Consistency in Video World Modeling","abstract":"Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions. Temporally- and spatially-consistent, long-term world modeling has been a long-standing problem, unresolved with even recent state-of-the-art models, due to the prohibitively expensive computational costs for long-context inputs. In this paper, we propose WorldPack, a video world model with efficient compressed memory, which significantly improves spatial consistency, fidelity, and quality in long-term generation despite much shorter context length. Our compressed memory consists of trajectory packing and memory retrieval; trajectory packing realizes high context efficiency, and memory retrieval maintains the consistency in rollouts and helps long-term generations that require spatial reasoning. Our performance is evaluated with LoopNav, a benchmark on Minecraft, specialized for the evaluation of long-term consistency, and we verify that WorldPack notably outperforms strong state-of-the-art models.","short_abstract":"Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions. Temporally- and spatially-consistent, long-term world modeling has been a long-standing problem, unresolved with even recent state-of-the...","url_abs":"https://arxiv.org/abs/2512.02473","url_pdf":"https://arxiv.org/pdf/2512.02473v1","authors":"[\"Yuta Oshima\",\"Yusuke Iwasawa\",\"Masahiro Suzuki\",\"Yutaka Matsuo\",\"Hiroki Furuta\"]","published":"2025-12-02T07:06:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}