LLQR+SAM pairs a slow learned geometry preconditioner with fast SAM perturbations to amplify escape from locally sharp 'potholes' while stabilizing flat basins, producing consistent gains over SAM and LLQR alone.
5th International Conference on Learning Representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Symmetrizing cross-entropy produces the unique convex multi-class unhinged loss, which locally approximates other symmetric losses, and enables new interpolating losses SGCE and alpha-MAE with competitive performance on noisy-label benchmarks.
Proposes forward replay of target hidden states from the first editing layer instead of backward spreading, claiming equivalent complexity but higher accuracy for LLM parameter editing.
citing papers explorer
-
Navigating Potholes with Geometry-Aware Sharpness Minimization
LLQR+SAM pairs a slow learned geometry preconditioner with fast SAM perturbations to amplify escape from locally sharp 'potholes' while stabilizing flat basins, producing consistent gains over SAM and LLQR alone.
-
Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
Symmetrizing cross-entropy produces the unique convex multi-class unhinged loss, which locally approximates other symmetric losses, and enables new interpolating losses SGCE and alpha-MAE with competitive performance on noisy-label benchmarks.
-
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
Proposes forward replay of target hidden states from the first editing layer instead of backward spreading, claiming equivalent complexity but higher accuracy for LLM parameter editing.