# Long-Video Generation

Few-step autoregressive video diffusion models gradually lose subject and scene information over long rollouts, and existing distillation targets do not constrain distant history separately. History Forcing builds a context residual from the difference between one autoregressive teacher's predictions with and without extra history, then weights it into the DMD or OPSD distillation target. A 1.3B student reaches a VBench quality score of 85.07 for 15-second generation and a VBench-Long aggregate of 79.82 for 60-second generation, and raises PlayWorld Evolution Quality from 2.35 to 2.70 when the camera leaves and returns.

Few-step autoregressive video diffusion models gradually lose subject and scene information over long rollouts, and existing distillation targets do not constrain distant history separately. History Forcing builds a context residual from the difference between one autoregressive teacher's predictions with and without extra history, then weights it into the DMD or OPSD distillation target. A 1.3B student reaches a VBench quality score of 85.07 for 15-second generation and a VBench-Long aggregate of 79.82 for 60-second generation, and raises PlayWorld Evolution Quality from 2.35 to 2.70 when the camera leaves and returns.

The work proposes Spatial Memory Intelligence (SMI), described as the first framework to systematically employ an understanding model (a multimodal large language model) for spatial-memory management in long-video world models, through four coordinated atomic operations: spatial clustering, within-cluster sparsification, action-aware retrieval, and reliability-aware filtering; experiments across multiple baselines, benchmarks, and world-model backbones report comprehensive improvements in memory sparsity, generation stability, and spatial consistency, supporting effectiveness and generalizability.

The work proposes Spatial Memory Intelligence (SMI), described as the first framework to systematically employ an understanding model (a multimodal large language model) for spatial-memory management in long-video world models, through four coordinated atomic operations: spatial clustering, within-cluster sparsification, action-aware retrieval, and reliability-aware filtering; experiments across multiple baselines, benchmarks, and world-model backbones report comprehensive improvements in memory sparsity, generation stability, and spatial consistency, supporting effectiveness and generalizability.