QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
HEaD+ detects object hallucinations early in diffusion generation via cross-attention maps, text, and a Predicted Final Image, raising complete image rates by 6-8% for four-object prompts and reducing time by up to 32%.
citing papers explorer
-
Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis
QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
-
Hallucination Early Detection in Diffusion Models
HEaD+ detects object hallucinations early in diffusion generation via cross-attention maps, text, and a Predicted Final Image, raising complete image rates by 6-8% for four-object prompts and reducing time by up to 32%.