Full Text Available

Note: Clicking the button above will open the full text document at the original institutional repository in a new window.

Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces

Saved in:
Bibliographic Details
Published in:ArXiv cs.LG Recent Papers
Format: Online Article RSS Article
Published: 2026
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864130790427721729
collection WordPress RSS
FRELIP Feed Integration
container_title ArXiv cs.LG Recent Papers
description
discipline_display Engineering & Technology
discipline_facet Engineering & Technology
format Online Article
RSS Article
genre Journal Article
id rss_article:48495
institution FRELIP
journal_source_facet ArXiv cs.LG Recent Papers
publishDate 2026
publishDateSort 2026
record_format rss_article
spellingShingle Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
sub_discipline_display Petroleum & Energy
sub_discipline_facet Petroleum & Energy
subject_display ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
subject_facet ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
title Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
title_auth Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
title_full Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
title_fullStr Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
title_full_unstemmed Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
title_short Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
title_sort beyond gaussian bottlenecks: topologically aligned encoding of vision-transformer feature spaces
topic ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
url https://arxiv.org/abs/2604.28122v1