SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation Paper • 2610.25844 • Published 24 days ago • 31
Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate Paper • 2610.04781 • Published Oct 8 • 18
Diffusing Scaled Text Embeddings Collection A student encoder distilled from T5Gemma-2, and ELF diffusion language models trained on the T5Gemma-2 and the distilled embeddings. • 6 items • Updated Oct 2 • 1
Scaling and Distilling Text Embeddings for Better Diffusibility Paper • 2610.01016 • Published Oct 1 • 25
Diffusing Scaled Text Embeddings Collection A student encoder distilled from T5Gemma-2, and ELF diffusion language models trained on the T5Gemma-2 and the distilled embeddings. • 6 items • Updated Oct 2 • 1
Scaling and Distilling Text Embeddings for Better Diffusibility Paper • 2610.01016 • Published Oct 1 • 25
Scaling and Distilling Text Embeddings for Better Diffusibility Paper • 2610.01016 • Published Oct 1 • 25
Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering Paper • 2409.02426 • Published Sep 4, 2024 • 1
Generalization of Diffusion Models Arises with a Balanced Representation Space Paper • 2512.20963 • Published Dec 24, 2025 • 2