PRADA uses probability ratios of autoregressive token sequences to detect and attribute images to specific generative models.
BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
DiVT clusters patch embeddings into coherent semantic units and adapts token count to image complexity, matching or exceeding baselines with fewer visual tokens on multimodal benchmarks.
citing papers explorer
-
PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
PRADA uses probability ratios of autoregressive token sequences to detect and attribute images to specific generative models.
-
A More Word-like Image Tokenization for MLLMs
DiVT clusters patch embeddings into coherent semantic units and adapts token count to image complexity, matching or exceeding baselines with fewer visual tokens on multimodal benchmarks.