SRNN: Spatiotemporal Relational Neural Network for Intuitive Physics Understanding

Abstract: Human prowess in intuitive physics remains unmatched by machines. To bridge this gap, we argue for a fundamental shift towards brain-inspired computational principles. This paper introduces the Spatiotemporal Relational Neural Network (SRNN), a model that establishes a unified neural representation for object attributes, relations, and timeline, with computations governed by a Hebbian Fire Together, Wire Together'' mechanism across dedicated \textit{What} and \textit{How} pathways. This unified representation is directly used to generate structured linguistic descriptions of the visual scene, bridging perception and language within a shared neural substrate. Moreover, unlike the prevalentpretrain-then-finetune'' paradigm, SRNN adopts a ``predefine-then-finetune'' approach. On the CLEVRER benchmark, SRNN achieves competitive performance. Our analysis further reveals a benchmark bias, outlines a path for a more holistic evaluation, and demonstrates SRNN's white-box utility for precise error diagnosis. Our work confirms the viability of translating biological intelligence into engineered systems for intuitive physics understanding.