ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
High-resolution image synthesis with latent diffusion models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
Prologue introduces dedicated prologue tokens to decouple generation and reconstruction in AR visual models, significantly improving generation FID scores on ImageNet while maintaining reconstruction quality.
LPNSR derives optimal intermediate noise for diffusion SR via MLE and implements it with an LR-guided noise predictor, reaching SOTA perceptual quality in 4 steps without text priors.
LiBaGS scores and selects synthetic data near decision boundaries using proximity, uncertainty, density, and validity, with boundary-gap allocation and marginal stopping to improve training accuracy.
citing papers explorer
-
ImageAttributionBench: How Far Are We from Generalizable Attribution?
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
-
Autoregressive Visual Generation Needs a Prologue
Prologue introduces dedicated prologue tokens to decouple generation and reconstruction in AR visual models, significantly improving generation FID scores on ImageNet while maintaining reconstruction quality.
-
LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction
LPNSR derives optimal intermediate noise for diffusion SR via MLE and implements it with an LR-guided noise predictor, reaching SOTA perceptual quality in 4 steps without text priors.
-
LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection
LiBaGS scores and selects synthetic data near decision boundaries using proximity, uncertainty, density, and validity, with boundary-gap allocation and marginal stopping to improve training accuracy.
- FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models