conftrace_

sharpness

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

transformer symmetries (1) log probability density (1) memorization metric (1) sharpness-aware regularization (1) temperature (1) circuit (1) stochasticity (1) generalisation (1) approximation (1) geodesic ball (1)

Papers

Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It ICML 2025 Softmax is not Enough (for Sharp Size Generalisation) ICML 2025 Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes ICML 2025 Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More ICML 2025