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
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
MICE modifies joint attention biases in Multimodal Diffusion Transformers to enable concurrent multi-instance edits while reducing semantic interference via user masks.
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.
-
Editing Everything Everywhere All at Once
MICE modifies joint attention biases in Multimodal Diffusion Transformers to enable concurrent multi-instance edits while reducing semantic interference via user masks.
-
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%.