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.
Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Experiments with a video-text-to-speech transformer show co-temporal positional indexing enables synchronization without timestamps, text and video supply complementary signals, and modality ordering creates a trade-off between in-domain accuracy and cross-domain generalization.
citing papers explorer
-
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.
-
Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis
Experiments with a video-text-to-speech transformer show co-temporal positional indexing enables synchronization without timestamps, text and video supply complementary signals, and modality ordering creates a trade-off between in-domain accuracy and cross-domain generalization.