发表机构
Sungkyunkwan University; Institute for Basic Science (IBS)（成均馆大学; 基础科学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ReGraph通过循环双流图模型揭示，泛化能力源于背侧视觉流中情境无关编码与网格样基元的共同涌现，且这些归纳偏置是关系结构形成的先决条件。
AI 中文摘要
泛化能力——即提取与情境无关的关系结构的能力——首先在何处涌现，仍是人工智能和神经科学领域的核心问题。这种能力的基础位于海马体上游的内嗅皮层，其中平行通路将内侧内嗅皮层（MEC）中的关系结构与外侧内嗅皮层中的感觉内容分离开来。然而，正如Eichenbaum所论证的，这种因子化可能更早起源，由背侧（"哪里"）和腹侧（"什么"）视觉流的分离所驱动。支持这一观点的是，网格样放电模式——MEC（情境无关编码）的一个标志——也出现在沿背侧通路的前置新皮层区域中。然而，这些表征如何沿上游通路在计算上形成仍属未知。为了在计算机中研究这一问题，我们开发了ReGraph，一种具有生物归纳偏置的循环双流图模型，包括视网膜驱动的流特化编码、背侧到腹侧的调制以及动态侧向连接。在动作基准Something-Something V2上训练后，ReGraph揭示了关系映射的通路特异性涌现：情境无关编码和网格样空间基元仅在延伸的背侧流中共同涌现。相比之下，它们在单流、无调制变体以及标准基线中的缺失表明，这些归纳偏置是关系结构的先决条件。至关重要的是，我们的事后分析表明，这些网格样基元可作为通过侧向连接进行信息处理的可复用路由模板。总之，我们的发现提供了一个计算解释：泛化可能不是一种在专门区域内突然涌现的能力，而是一种在感觉信息被解析为层级视觉处理的因子化流时就已经形成的属性。
英文摘要
Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neuroscience. The foundation for this capacity lies upstream of the hippocampus, within the entorhinal cortex, where parallel pathways dissociate relational structure in the medial entorhinal cortex (MEC) from sensory content in the lateral entorhinal cortex. However, as Eichenbaum argued, such factorization likely originates earlier, driven by the segregation of the dorsal ('where') and ventral ('what') visual streams. Supporting this, grid-like firing patterns--a signature of MEC (context-invariant codes)--also appear in preceding neocortical regions along the dorsal pathway. Yet, how such representations are computationally formed along upstream pathways remains unknown. To investigate this in silico, we developed ReGraph, a recurrent dual-stream graph model with biological inductive biases, including retina-driven stream-specialized encoding, dorsal-to-ventral modulation, and dynamic lateral connectivity. Trained on the action benchmark Something-Something V2, ReGraph revealed a pathway-specific emergence of relational mapping: context-invariant codes and grid-like spatial bases uniquely co-emerged along the extended dorsal stream. In contrast, their absence in single-stream, unmodulated variants, and standard baselines implies that these inductive biases are prerequisites for relational structures. Crucially, our post-hoc analyses demonstrated that these grid-like bases serve as reusable routing templates for information processing via lateral connectivity. Together, our findings provide a computational account that generalization may not be a faculty that emerges abruptly within a dedicated region, but a property that already takes shape as sensory information is parsed into factorized streams of hierarchical visual processing.
Comments29 pages, 6 figures
