发表机构
KAIST; Sony Group Corporation; Imperial College London（韩国科学技术院; 索尼集团公司; 伦敦帝国理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对世界模型中情景记忆检索线索不可靠的问题，提出未来感知回忆（FAR）框架，利用未来感知预测监督和自适应多线索评分学习检索，在多个设置中优于手工设计方法。
AI 中文摘要
世界模型根据当前经验和动作预测未来的观察结果，然而预测可能依赖于很久以前看到的观察结果。情景记忆保存过去的观察结果以供日后回忆；然而，随着记忆的积累，它引发了一个基本问题：哪些记忆对当前预测有用，以及应该信任哪些可用的检索线索来找到它们？这具有挑战性，因为基于新近性、姿态重叠或视觉相似性的固定标准在不同环境和查询中可能不可靠。我们提出了未来感知回忆（FAR），一个从未来感知的预测监督和自适应多线索评分中学习情景回忆的框架。在训练期间，FAR通过给定回忆上下文的已实现未来的条件对数似然来衡量预测效用，该似然由负扩散预测损失近似，并用它来训练一个在推理时保持未来盲的检索器。该检索器学习线索特定的相关性，并在选择记忆时自动确定对于每个查询信任哪些可用的检索线索，如时间、姿态、视觉和音频。在三个互补的设置中，即使使用相同的检索线索，FAR也优于手工设计的回忆，自动适应信任哪些可用线索，并在世界变化时回忆正确的历史。总之，这些结果确立了FAR作为世界模型中情景记忆访问的一种灵活、有原则的方法。
英文摘要
World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic memory preserves past observations for later recall; however, as memory accumulates, it raises a fundamental question: which memories are useful for the current prediction, and which available retrieval cues should be trusted to find them? This is challenging because fixed criteria based on recency, pose overlap, or visual similarity can be unreliable across environments and queries. We propose Future-Aware Recall (FAR), a framework that learns episodic recall from future-aware predictive supervision and adaptive multi-cue scoring. During training, FAR measures predictive utility by the conditional log-likelihood of the realized future given recalled context, approximated by negative diffusion prediction loss, and uses it to train a retriever that remains future-blind at inference. The retriever learns cue-specific relevance and automatically determines which available retrieval cues, such as time, pose, vision, and audio, to trust for each query when selecting memories. Across three complementary settings, FAR outperforms hand-designed recall even with the same retrieval cues, automatically adapts which available cues to trust, and recalls the right history as the world changes. Together, these results establish FAR as a flexible, principled approach to episodic memory access in world models.
CommentsPreprint, Project Page: https://1202kbs.github.io/FAR-Project-Page/
