10 papers
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…
Entropic Context Shaping: Information-Theoretic Filtering for Context-Aware LLM Agents
Hyunjun Kim
Context engineering for large language model (LLM) agents requires distinguishing pragmatically useful information from misleading distractors. We introduce Entropic Context Shapin…
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…
Defensive M2S: Training Guardrail Models on Compressed Multi-turn Conversations
Hyunjun Kim
Guardrail models are essential for ensuring the safety of Large Language Model (LLM) deployments, but processing full multi-turn conversation histories incurs significant computati…
DrawingBench: Evaluating Spatial Reasoning and UI Interaction Capabilities of Large Language Models through Mouse-Based Drawing Tasks
Hyunjun Kim, Sooyoung Ryu
As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and audita…