Metraipolis › archive › dc_db8a8059920c
ReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual Streams — arXiv:2610.07962
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07962
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:21:24.241Z
- SHA-256 of the archived text
f7d02bf1f2cdcb34917e151b4aa517f39b3e1889dc240ca6e30c294589dd2379- Stable URL of this page
https://metraipolis.com/documento/dc_db8a8059920c
How to cite
ReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual Streams — arXiv:2610.07962 — arXiv (en), https://arxiv.org/abs/2610.07962 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db8a8059920c (Metraipolis archive dc_db8a8059920c, sha256 f7d02bf1f2cdcb34917e151b4aa517f39b3e1889dc240ca6e30c294589dd2379)
BibTeX
@misc{dcdb8a8059920c,
title = {ReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual Streams — arXiv:2610.07962},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07962},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db8a8059920c; sha256 f7d02bf1f2cdcb34917e151b4aa517f39b3e1889dc240ca6e30c294589dd2379},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07962. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2610.07962 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:15:24.788Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).