Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Jian, Birsak, Michael, Cui, Wenqing, Li, Zhenyu, Wonka, Peter
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910005338308608
author Shi, Jian
Birsak, Michael
Cui, Wenqing
Li, Zhenyu
Wonka, Peter
author_facet Shi, Jian
Birsak, Michael
Cui, Wenqing
Li, Zhenyu
Wonka, Peter
contents This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and spatial reasoning. Our findings clarify the role of PEs as a causal mechanism that governs spatial structure in ViT representations. Our code is provided in https://github.com/shijianjian/vit-geometry-probes
format Preprint
id arxiv_https___arxiv_org_abs_2601_22231
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning
Shi, Jian
Birsak, Michael
Cui, Wenqing
Li, Zhenyu
Wonka, Peter
Computer Vision and Pattern Recognition
This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and spatial reasoning. Our findings clarify the role of PEs as a causal mechanism that governs spatial structure in ViT representations. Our code is provided in https://github.com/shijianjian/vit-geometry-probes
title Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.22231