AI 中文总结
本文提出WorldPlay2交互式世界模型，通过分解混合控制接口、压缩记忆令牌和稳定强迫蒸馏，实现实时响应与长视界一致性，并在实验中展现优越性能。
AI 中文摘要
交互式世界模型需要实时响应多种控制并保持长视界一致性。然而，对异构控制的建模仍然困难，而爆炸性的上下文和不稳定的蒸馏阻碍了同时实现长视界一致性和实时响应。在本文中，我们提出了WorldPlay2，一种交互式世界模型，它将分解的混合控制接口与压缩记忆和稳定蒸馏的协同设计相结合。1) 我们的分解混合控制接口将帧对齐的动作控制与结构化语义控制集成在一起，后者显式地分离场景外观、角色身份和动态语义事件，从而促进有效的控制学习。2) 为了实现高效的长视界建模，我们将历史上下文压缩为紧凑的记忆令牌，由自回归学生模型和双向教师模型共享。这种设计使得能够进行逐片段、记忆条件的分数评估，而不是联合处理整个长轨迹，从而大幅减少蒸馏开销。3) 我们进一步提出了稳定强迫（Stable Forcing），它通过几步策略初始化自回归学生模型，并利用全轨迹回放来保持长视界轨迹的质量，确保稳健且稳定的蒸馏。大量实验证明了我们模型的强泛化能力以及相较于现有方法的优越性能。
英文摘要
Interactive world models require responding in real time to versatile controls and maintaining long-horizon consistency. However, modeling heterogeneous controls remains difficult, while explosive contexts and unstable distillation impede achieving both long-horizon consistency and real-time responsiveness. In this paper, we present WorldPlay2, an interactive world model that couples a factorized hybrid control interface with a co-design of compressed memory and stable distillation. 1) Our factorized hybrid control interface integrates frame-aligned action control with structured semantic control that explicitly disentangles scene appearance, character identity, and dynamic semantic events, thereby facilitating effective control learning. 2) To achieve efficient long-horizon modeling, we compress historical contexts into compact memory tokens shared by the autoregressive student and the bidirectional teacher. This design enables clip-wise, memory-conditioned score evaluation instead of jointly processing an entire long rollout, substantially reducing distillation overhead. 3) We further propose Stable Forcing, which initializes the autoregressive student via a few-step strategy and leverages full-rollout replay to preserve the quality of long-horizon rollouts, ensuring robust and stable distillation. Extensive experiments demonstrate the strong generalizability of our model and its superior performance compared to existing methods.
Commentsproject page: https://worldplay2.github.io/
