SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

World models allow agents to simulate the consequences of actions in imagined environments for planning, control, and long-horizon decision-making. However, existing autoregressive world models struggle with visually coherent predictions due to disrupted spatial structure, inefficient decoding, and inadequate motion modeling. In response, we propose Scale-wise Autoregression with Motion PrOmpt (SAMPO), a hybrid framework that combines visual autoregressive modeling for intra-frame generation with causal modeling for next-frame generation. Specifically, SAMPO integrates temporal causal decoding with bidirectional spatial attention, which preserves spatial locality and supports parallel decoding within each scale. This design significantly enhances both temporal consistency and rollout efficiency. To further improve dynamic scene understanding, we devise an asymmetric multi-scale tokenizer that preserves spatial details in observed frames and extracts compact dynamic representations for future frames, optimizing both memory usage and model performance. Additionally, we introduce a trajectory-aware motion prompt module that injects spatiotemporal cues about object and robot trajectories, focusing attention on dynamic regions and improving temporal consistency and physical realism. Extensive experiments show that SAMPO achieves competitive performance in action-conditioned video prediction and model-based control, improving generation quality with 4. 4× faster inference. We also evaluate SAMPO's zero-shot generalization and scaling behavior, demonstrating its ability to generalize to unseen tasks and benefit from larger model sizes.

Authors

• Sen Wang
• Jingyi Tian
• Le Wang Xi'an Jiaotong University
• Zhimin Liao
• Huaiyi Dong
• Kun Xia Xi'an Jiaotong University
• Sanping Zhou Xi'an Jiaotong University
• Wei Tang School of Computer Science and Engineering, Southeast University, Nanjing 210096, China Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China
• Gang Hua Multimodal Experiences Research Lab, Dolby Laboratories

Keywords

No keywords are indexed for this paper.