Echo-Memory：动作世界模型中记忆的受控研究
Echo-Memory: A Controlled Study of Memory in Action World Models
AI总结：
提出Echo-Memory框架，通过控制变量法研究动作条件世界模型中的记忆机制，发现原始上下文容量和块状状态空间递归对开放域返回任务至关重要。
摘要：
我们提出\textbf{Echo-Memory}，对动作条件世界模型中的记忆机制进行受控研究。这些模型从第一帧、文本提示和相机动作序列生成多段视频，但其核心失败往往是记忆而非局部图像合成：当相机离开并返回时，场景或显著物体可能悄然改变。现有记忆设计难以比较，因为增益与骨干网络、训练、检索和评估差异纠缠在一起。Echo-Memory固定了动作到视频的接口，仅改变生成器存储和读取历史的方式。在共享的视频扩散骨干网络、优化器、相机动作表示、采样器和评估流程下，我们比较了原始上下文、基于压缩的记忆、具有不同读取路径的空间摘要以及状态空间递归。这种匹配矩阵分离了四个通常混淆的轴：\emph{容量}、\emph{压缩}、\emph{读取}和\emph{递归}。我们还通过三个分支协议评估记忆：重放质量、域内循环重访和开放域返回探测。这些分支通常不一致，表明重放保真度不足以作为记忆世界的代理。得出三个发现。原始上下文是一个强大的容量基线，并且比重放指标更能改善开放域返回。紧凑性不能免费替代容量：激进的混合压缩记忆会丢失返回所需的显著证据。最后，块状状态空间递归是我们矩阵中最强的开放域返回机制，表明隐式记忆的结构与是否使用记忆同样重要。这些结果为在孤立的重放指标之外研究动作世界模型中的记忆提供了一个紧凑的协议。
英文摘要：
We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos from a first frame, text prompt, and camera-action sequence, but their central failure is often memory rather than local image synthesis: after the camera leaves and returns, the scene or salient object may silently change. Existing memory designs are hard to compare because gains are entangled with backbone, training, retrieval, and evaluation differences. Echo-Memory fixes the action-to-video interface and varies only how history is stored and read by the generator. Under a shared video diffusion backbone, optimizer, camera-action representation, sampler, and evaluation pipeline, we compare raw context, compression-based memory, spatial summaries with different read-out paths, and state-space recurrence. This matched matrix separates four otherwise conflated axes: \emph{capacity}, \emph{compression}, \emph{read-out}, and \emph{recurrence}. We also evaluate memory through a three-branch protocol: replay quality, in-domain loop revisit, and open-domain return probes. The branches routinely disagree, showing that replay fidelity is not a sufficient proxy for remembering a world. Three findings follow. Raw context is a strong capacity baseline and improves open-domain return far more than it improves replay metrics. Compactness is not a free substitute for capacity: aggressive spatial and hybrid-compression memories lose the salient evidence needed for return. Finally, block-wise state-space recurrence is the strongest open-domain return mechanism in our matrix, showing that the structure of implicit memory matters as much as the decision to use it. These results provide a compact protocol for studying memory in action world models beyond isolated replay metrics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
