AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

How Do Transformers Learn to Represent Symmetries?

arXiv · AI, language, vision and robotics · article · Oct 7, 2026 · UTC

Training Transformer-based architectures with finite data augmentation has become an increasingly popular approach in geometric machine learning. Despite its empirical success, the interplay between the Transformer architecture, invariance to different symmetries, and augmentation budgets remains underexplored. In this paper, we study the ability of a vanilla Transformer to learn various symmetries through finite data augmentation for point cloud datasets. We identify an ordering of increasing learnability across the following symmetry groups: (i) non-angle-preserving symmetries, (ii) angle-pr

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-08T10:02:25.305Z. This is not the publication date.