Introduces a causal intervention framework with new metrics for mechanistic interpretability of VAEs and reports empirical findings from extensive experiments on multiple models and datasets.
Testing relational understanding in text-guided image generation,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
citing papers explorer
-
A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders
Introduces a causal intervention framework with new metrics for mechanistic interpretability of VAEs and reports empirical findings from extensive experiments on multiple models and datasets.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.