Alaya-EVOKE：从线性扩展监督到无尽世界

摘要

交互式世界模型必须支持持久记忆、响应式交互和长时程生成，然而这些要求对模型施加了相互冲突的需求。在去噪器上下文或键值缓存中维护历史会带来不断增长的额外开销，迫使在会话长度与记忆保留之间进行权衡；同时，低延迟交互依赖少步生成，而少步生成的能力受限于其教师模型。Evoke 通过外部化持久世界状态并重新设计面向长时程交互式生成的教师模型，解决了这两个局限。场景几何信息维护在一个外部的、按相机索引的世界状态库中，仅检索与当前视角相关的信息，从而使去噪器上下文在会话增长时保持有界。我们没有将教师模型视为固定的生成器，而是将其设计用于长时程监督：其稀疏注意力结合了分块分组、选定远帧检索以及线性注意力全局状态，在实现内存和计算线性增长的同时，能够对长时程进行监督。这种监督暴露了在短窗口内保持局部合理性的内容漂移，而逐块条件化则支持在整个序列中进行提示词更改和事件控制。在自强迫展开下应用的 30 秒分布匹配目标，将这两项能力迁移至不使用无分类器引导的三步学生模型，从而在保持响应式条件化的同时，提升对长期漂移的抵抗能力。凭借有界上下文和循环外部记忆，Evoke 支持开放式、持续演化的生成；在单块 H200 上、384×640 分辨率下，每个 1.5 秒的块仅需 2.11 秒即可生成。作为三步世界模型，Evoke 在 WBench 上达到了最先进水平，同时在 VBench-Long 和 VBench-2.0 上保持了竞争力。

English

Interactive world models must support persistent memory, responsive interaction, and long-horizon generation, yet these requirements place conflicting demands on the model. Maintaining history in the denoiser context or key-value cache incurs growing cost, forcing a trade-off between session length and retained memory, while low-latency interaction relies on few-step generation whose capabilities are bounded by its teacher. Evoke addresses both limitations by externalizing persistent world state and redesigning the teacher for long-horizon interactive generation. Scene geometry is maintained in an external, camera-indexed world state bank, from which only view-relevant information is retrieved, keeping the denoiser context bounded as the session grows. Rather than treating the teacher as a fixed generator, we design it for long-horizon supervision: its sparse attention combines chunk-wise grouping, retrieval of selected distant frames, and a linear-attention global state, yielding linear growth in memory and compute while enabling supervision over long horizons. Such supervision exposes content drift that stays locally plausible within short windows, while per-chunk conditioning enables prompt changes and event control throughout the sequence. A 30-second distribution-matching objective, applied under self-forced rollouts, transfers both capabilities to a three-step student that uses no classifier-free guidance, improving resistance to long-term drift while preserving responsive conditioning. With bounded context and recurrent external memory, Evoke supports open-ended, continuously evolving generation; on a single H200 at 384times 640, each 1.5,s chunk is generated in 2.11,s. As a three-step world model, Evoke achieves state-of-the-art performance on WBench while remaining competitive on VBench-Long and VBench-2.0.