UR-JEPA applies uniform rectifiability regularization via a smoothed Carleson square function to JEPA training, producing embeddings with 4-5 order PCA spectral drop at dimension 20-25 and lower seed variance than Gaussian regularization on Inet10, Galaxy10, and EuroSAT.
NeurIPS 2019; arXiv preprint matches proceedings
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Introduces the Patnaik-Pearson intrinsic dimension estimator, proves some of its properties, relates it to HTSR/SETOL for Pareto spectra, and applies it to track embedding dimension evolution in BERT-base and DeepSeek-R1-Distill-Qwen-1.
Geometry maps the conditions for perfect last-layer theft in transformers and demonstrates that full hidden-network reverse engineering is impossible from final outputs.
citing papers explorer
-
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
UR-JEPA applies uniform rectifiability regularization via a smoothed Carleson square function to JEPA training, producing embeddings with 4-5 order PCA spectral drop at dimension 20-25 and lower seed variance than Gaussian regularization on Inet10, Galaxy10, and EuroSAT.
-
Patnaik-Pearson intrinsic dimension for internal representations of neural networks
Introduces the Patnaik-Pearson intrinsic dimension estimator, proves some of its properties, relates it to HTSR/SETOL for Pareto spectra, and applies it to track embedding dimension evolution in BERT-base and DeepSeek-R1-Distill-Qwen-1.
-
The Geometry of Last-Layer Model Stealing
Geometry maps the conditions for perfect last-layer theft in transformers and demonstrates that full hidden-network reverse engineering is impossible from final outputs.
- The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior