Introduces a Bridge latent interface that maps mismatched student latents into teacher space, enabling distillation from modern diffusion teachers to compact one-step students and raising SD 1.5 HPSv3 from 5.4 to 9.4 while keeping one-step speed.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
EquiSteer reduces average demographic parity gaps by up to 87% in Stable Diffusion variants and SANA via inference-time cross-attention steering with minimal impact on image quality or alignment.
citing papers explorer
-
Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
Introduces a Bridge latent interface that maps mismatched student latents into teacher space, enabling distillation from modern diffusion teachers to compact one-step students and raising SD 1.5 HPSv3 from 5.4 to 9.4 while keeping one-step speed.
-
EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
EquiSteer reduces average demographic parity gaps by up to 87% in Stable Diffusion variants and SANA via inference-time cross-attention steering with minimal impact on image quality or alignment.
- LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models