1 citations · 1 across the 10 of their papers we have counts for
4 papers · 1 filter
LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
Hyunjun Kim
Weight initialization remains decisive for neural network optimization, yet existing methods are largely layer-agnostic. We study initialization for deeply-supervised architectures…
HOLOGRAPH: Active Causal Discovery via Sheaf-Theoretic Alignment of Large Language Model Priors
Hyunjun Kim
Causal discovery from observational data remains fundamentally limited by identifiability constraints. Recent work has explored leveraging Large Language Models (LLMs) as sources o…
Geometric Regularization in Mixture-of-Experts: The Disconnect Between Weights and Activations
Hyunjun Kim
Mixture-of-Experts (MoE) models achieve efficiency through sparse activation, but the role of geometric regularization in expert specialization remains unclear. We apply orthogonal…
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation
Hyunjune Kim, Sangyong Lee, Simon S. Woo
Recently, serious concerns have been raised about the privacy issues related to training datasets in machine learning algorithms when including personal data. Various regulations i…