DiTs use either a two-stage cross-attention circuit or text-token fusion circuit for spatial relations depending on the text encoder, achieving near-perfect in-domain accuracy but differing out-of-domain robustness.
Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
3 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
3
Pith papers citing it
2
external citations · external index
years
2026 3verdicts
UNVERDICTED 3representative 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.
Causal probing of attention in audio separation transformers identifies dual pathways and asynchronous convergence, enabling a training-free Layer-Selective Attention Caching method that reduces self-attention computation by ~25% with negligible quality loss.
citing papers explorer
-
Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
DiTs use either a two-stage cross-attention circuit or text-token fusion circuit for spatial relations depending on the text encoder, achieving near-perfect in-domain accuracy but differing out-of-domain robustness.
-
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.
-
Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models
Causal probing of attention in audio separation transformers identifies dual pathways and asynchronous convergence, enabling a training-free Layer-Selective Attention Caching method that reduces self-attention computation by ~25% with negligible quality loss.