LASAR：面向时空推理的潜在认知地图
LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map
ST-CRL 用仿真中带时空标注的查询构造对比样本对，把碎片化经验压成内部认知地图，这一自监督信号可直接迁移到任何需要长程空间记忆的视觉导航或具身问答模型训练中。
原文依据 ST-CRL leverages spatio-temporal cues from cognitive queries generated through annotated spatio-temporal context in simulation to build sample pairs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论具身智能的一个根本性挑战在于验证智能体是否构建了空间结构的内部模型，还是仅仅学会了模仿特定任务的专家轨迹。这一点至关重要，因为根植于以动作为中心的任务（如视觉语言导航 VLN）和以推理为中心的任务（如具身问答 EQA）的基础性方法往往共享一个共同局限：它们缺乏一种学习信号，迫使智能体在长程、碎片化的经验之上编码细粒度的空间关系（如拓扑或距离）。为解决这一问题，我们首先提出 LASAR，一种具有双记忆系统的架构，旨在同时维护情景经验与语义认知地图。随后我们引入时空上下文表征学习（ST-CRL），一种用于训练该架构的对比目标。ST-CRL 利用仿真中由带标注的时空上下文生成的认知查询所提供的时空线索来构建样本对，从而由智能体的经验中形成内部认知地图。实验表明，我们的方法在标准 VLN-CE 与 VSI-Bench 基准上的零样本泛化均取得 2%–3.5% 的提升。我们还证明了所提出的认知地图具有较高的自一致性。
英文原文摘要 1231 字符
A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert trajectories. This is critical as foundational approaches rooted in action-centric tasks (e.g., VLN) and reasoning-centric tasks (e.g., EQA) often share a common limitation: they lack a learning signal that forces them to encode fine-grained spatial relationships (like topology or distance) over long-range, fragmented experiences. To address this, we first propose LASAR, an architecture featuring a dual-memory system designed to maintain both episodic experiences and a semantic cognitive map. We then introduce Spatio-temporal Contextual Representation Learning (ST-CRL), a contrastive objective designed to train this architecture. ST-CRL leverages spatio-temporal cues from cognitive queries generated through annotated spatio-temporal context in simulation to build sample pairs, thereby forming the internal cognitive map from the agent's experiences. Experiments demonstrate that our method achieves 2%-3.5% gains in both zero-shot generalization on standard VLN-CE and VSI-Bench benchmarks. We also demonstrate that our proposed cognitive map has high self-consistency.