54 citations · 324 across the 32 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Adversarial Learning of Classifier-Free Guidance Schedules
Ashwini Pokle, Alexandre Galashov, Arnaud Doucet +2
Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scal…
cs.LG2026
The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
Mojtaba Sahraee-Ardakan, Mauricio Delbracio, Peyman Milanfar
Autonomous (noise-agnostic) generative models, such as Equilibrium Matching and blind diffusion, challenge the standard paradigm by learning a single, time-invariant vector field t…