SPACE：基于反事实驱逐的稀疏预测吸引子用于流式视频记忆
SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory
浏览论文内容
中文总结 AI 辅助
针对流式视频记忆驱逐决策影响累积的问题，提出SPACE方法，利用冻结JEPA预测未来表示进行反事实驱逐，并引入MABS-Bench基准，在多个数据集上提升任务性能并降低预测漂移。
中文摘要 AI 辅助
固定容量的流式视频记忆需要反复进行驱逐决策，这些决策的影响会随时间累积。然而，现有策略主要根据保留信息或下游准确率进行评估，而反复更新如何改变记忆所支持的未来状态在很大程度上未被研究。我们将记忆的预测状态定义为由其保留历史所支持的未来表示，并将驱逐问题表述为对该空间中转换的反事实控制。我们提出了SPACE（基于反事实驱逐的稀疏预测吸引子），它使用冻结的多视界JEPA来预测由替代驱逐行为所引发的未来表示。反事实效用识别出对未来有用的替代方案，而缓慢的预测盆地几何结构则决定何时纠正可避免的漂移以及何时适应持续的预测变化，而无需在线参数更新。我们进一步引入了MABS-Bench，它在匹配的因果流和记忆预算下评估未来任务充分性、域内预测稳定性、转换响应性以及扰动恢复能力。在多个视频数据集上，SPACE在降低预测状态漂移的同时，持续提升了数据集原生任务的性能。
英文摘要
Fixed-capacity streaming video memory requires repeated eviction decisions whose effects accumulate over time. Yet existing policies are evaluated primarily in terms of retained information or downstream accuracy, leaving how repeated updates alter the futures supported by memory largely unexamined. We define a memory's predictive state as the future representations supported by its retained history and formulate eviction as counterfactual control over transitions in this space. We introduce SPACE (Sparse Predictive Attractor via Counterfactual Eviction), which uses a frozen multi-horizon JEPA to predict the future representations induced by alternative eviction actions. Counterfactual utility identifies future-useful alternatives, while slow predictive-basin geometry determines when to correct avoidable drift and when to adapt to sustained predictive change, without online parameter updates. We further introduce MABS-Bench, which evaluates future-task sufficiency, within-regime predictive stability, transition responsiveness, and perturbation recovery under matched causal streams and memory budgets. Across multiple video datasets, SPACE yields consistent improvements in dataset-native task performance while reducing predictive-state drift.
