{"ID":2843772,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06761","arxiv_id":"2511.06761","title":"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. On the CLEVRER benchmark, SRNN achieves competitive performance, thereby confirming its capability to represent essential spatiotemporal relations from the visual stream. Cognitive ablation analysis further reveals a benchmark bias, outlining a path for a more holistic evaluation. Finally, the white-box nature of SRNN enables precise pinpointing of error root causes. Our work provides a proof-of-concept that confirms the viability of translating key principles of biological intelligence into engineered systems for intuitive physics understanding in constrained environments.","short_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 attribute...","url_abs":"https://arxiv.org/abs/2511.06761","url_pdf":"https://arxiv.org/pdf/2511.06761v2","authors":"[\"Fei Yang\"]","published":"2025-11-10T06:43:42Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}