Fixed-Point Distillation constructs one-step correction targets for discrete diffusion generators via partial corruption and single teacher refinement, lifted into continuous features with a multi-bandwidth drift loss and straight-through estimation.
Diff-instruct: A universal approach for transferring knowledge from pre-trained diffusion models.Advances in Neural Information Processing Systems, 36:76525–76546, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration
Fixed-Point Distillation constructs one-step correction targets for discrete diffusion generators via partial corruption and single teacher refinement, lifted into continuous features with a multi-bandwidth drift loss and straight-through estimation.