AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Photolithography Overlay Map Generation with Implicit Knowledge Distillation Diffusion Transformer

Yuan-Fu Yang, Hsiu-Hui Hsiao

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add implicit knowledge distillation and gated cross-attention vs baseline DiTsIKDDiT · MPOM, 500k iterationsFID: 14.1 -> 6.8Improved
add classifier-free guidanceIKDDiT · MPOMFID: 6.64 -> 2.68Improved
add classifier-free guidanceIKDDiT · MPOMsFID: 5.24 -> 6.12Improved
use gated cross-attention instead of multi-head cross-attention (ablation)IKDDiT with UCE · MPOM ablationFID-15k: 49.83 -> 24.66Improved
use gated cross-attention instead of adaptive normalization conditioning (ablation)IKDDiT with UCE · MPOM ablationFID-15k: 37.42 -> 24.66Improved
use unified contrastive embedding instead of CLIP encoder (ablation)IKDDiT gated cross-attention · MPOM ablationFID-15k: 30.34 -> 24.66Improved
use implicit discriminator instead of self-supervised discrimination (ablation)IKDDiT · MPOM ablationFID-15k: 30.39 -> 24.66Improved
mask 50% of tokens instead of none (ablation)IKDDiT · MPOM ablationFID-15k: 27.46 -> 24.66Improved
raise mask ratio from 50% to 70% (ablation)IKDDiT · MPOM ablationFID-15k: 24.66 -> 123.85Hurt
add MAE reconstruction loss (lambda1 from 0 to 0.1) (ablation)IKDDiT · MPOM ablation, lambda2=0.01FID-15k: 35.07 -> 24.66Improved
add discriminator loss (lambda2 from 0 to 0.01) (ablation)IKDDiT · MPOM ablation, lambda1=0.1FID-15k: 29.72 -> 24.66Improved
raise lambda1 from 0.1 to 1 (ablation)IKDDiT · MPOM ablation, lambda2=0.01FID-15k: 24.66 -> 27.33Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy