Papers by Dean F. Hougen
Mechanistic Interpretability of Text-to-Image Diffusion Models via Cross-Attention Interventions (2026.findings-acl)
Copied to clipboard
| Challenge: | Text-to-image diffusion models generate high quality images through iterative denoising, but their internal mechanisms for grounding prompt semantics into visual structure remain unclear. |
| Approach: | They propose a mechanistic interpretability framework that probes how individual prompt tokens are represented and utilized during the denoising process. |
| Outcome: | The proposed framework enables module-wise and head-wise attribution of semantic changes across denoising timesteps. |