In sparse regimes, models exploit normal alignment of Jacobians to minimize loss and maximize robustness; GrokAlign induces this alignment to accelerate training and RFAMs improve adversarial robustness.
AugMix: A Simple Method to Improve Robustness and Uncertainty Under Data Shift
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Geometric Structure of Models Learning Sparse Data
In sparse regimes, models exploit normal alignment of Jacobians to minimize loss and maximize robustness; GrokAlign induces this alignment to accelerate training and RFAMs improve adversarial robustness.