The subspace intervention framework reveals that pre-training objectives shape how ViTs encode geometric information in compressible low-rank subspaces, with peak precision at intermediate layers.
arXiv preprint arXiv:2410.07687 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
citing papers explorer
-
Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention
The subspace intervention framework reveals that pre-training objectives shape how ViTs encode geometric information in compressible low-rank subspaces, with peak precision at intermediate layers.
-
Pointwise Generalization in Deep Neural Networks
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.