---
res:
  bibo_abstract:
  - "Neural models learn representations of high-dimensional data on low-dimensional\r\nmanifolds.
    Multiple factors, including stochasticities in the training process, model\r\narchitectures,
    and additional inductive biases, may induce different representations,\r\neven
    when learning the same task on the same data. However, it has recently been\r\nshown
    that when a latent structure is shared between distinct latent spaces, relative\r\ndistances
    between representations can be preserved, up to distortions. Building\r\non this
    idea, we demonstrate that exploiting the differential-geometric structure of\r\nlatent
    spaces of neural models, it is possible to capture precisely the transformations\r\nbetween
    representational spaces trained on similar data distributions. Specifically,\r\nwe
    assume that distinct neural models parametrize approximately the same underlying
    manifold, and introduce a representation based on the pullback metric\r\nthat
    captures the intrinsic structure of the latent space, while scaling efficiently\r\nto
    large models. We validate experimentally our method on model stitching and\r\nretrieval
    tasks, covering autoencoders and vision foundation discriminative models,\r\nacross
    diverse architectures, datasets, pretraining schemes and modalities. Code is\r\navailable
    at https://github.com/marc0git/RelativeGeodesics.@eng"
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Hanlin
      foaf_name: Yu, Hanlin
      foaf_surname: Yu
  - foaf_Person:
      foaf_givenName: Berfin
      foaf_name: Inal, Berfin
      foaf_surname: Inal
  - foaf_Person:
      foaf_givenName: Georgios
      foaf_name: Arvanitidis, Georgios
      foaf_surname: Arvanitidis
  - foaf_Person:
      foaf_givenName: Søren
      foaf_name: Hauberg, Søren
      foaf_surname: Hauberg
  - foaf_Person:
      foaf_givenName: Francesco
      foaf_name: Locatello, Francesco
      foaf_surname: Locatello
      foaf_workInfoHomepage: http://www.librecat.org/personId=26cfd52f-2483-11ee-8040-88983bcc06d4
    orcid: 0000-0002-4850-0683
  - foaf_Person:
      foaf_givenName: Marco
      foaf_name: Fumero, Marco
      foaf_surname: Fumero
      foaf_workInfoHomepage: http://www.librecat.org/personId=1c1593eb-393f-11ef-bb8e-ab4f1e979650
  bibo_doi: 10.52202/085713-3769
  bibo_volume: 38
  dct_date: 2025^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/1049-5258
  - http://id.crossref.org/issn/9798331338275
  dct_language: eng
  dct_publisher: Neural Information Processing Systems Foundation@
  dct_title: Connecting neural models latent geometries with relative geodesic representations@
...