Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
One Inverse Step is a Convex Program: Bayes-Limit Calibration of Diffusion Inversion
Gordei Verbii
One implicit DDIM inversion step is the cheapest probe of whether a pretrained diffusion model encodes local manifold geometry. It is the stationarity condition of an explicit pote…
stat.ML2026
The Distributional View of Knowledge Distillation
Gordei Verbii, Juho Lee
Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the standard objectives compare them pointwise: a Kullback-Leibler gradient is blind…