AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

AdaGen: Learning Adaptive Policy for Image Synthesis

Zanlin Ni, Yulin Wang, Yue Hua, Renping Zhou, Jiayi Guo, Jun Song, Bo Zheng, Gao Ming Huang

TPAMI 2025 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation

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
learn the generation schedule instead of using the hand-designed one (ablation)MaskGIT-S · ImageNet 256 (T=4)FID-50K: 7.65 -> 5.40Improved
learn the generation schedule instead of using the hand-designed one (ablation)DiT-XL · ImageNet 256 (T=4)FID-50K: 9.71 -> 6.03Improved
make the learned policy sample-adaptive (ablation)MaskGIT-S · ImageNet 256 (T=4)FID-50K: 5.40 -> 4.54Improved
make the learned policy sample-adaptive (ablation)DiT-XL · ImageNet 256 (T=4)FID-50K: 6.03 -> 5.31Improved
add repeated sampling selected by the adversarial reward model (ablation)AdaGen-MaskGIT-L · ImageNet 256 (T=32)FID-50K: 2.28 -> 2.07Improved
add lookahead sampling with the value network (K=2) to repeated sampling (ablation)AdaGen-MaskGIT-L · ImageNet 256 (T=32)FID-50K: 2.07 -> 1.94Improved
add repeated sampling selected by the adversarial reward model (ablation)AdaGen-DiT-XL · ImageNet 256 (T=16)FID-50K: 2.19 -> 2.06Improved
increase repeated sampling trials from 0 to 3 (with lookahead) (ablation)AdaGen-MaskGIT-L · ImageNet 256 (T=32)FID-50K: 2.28 -> 1.81Improved
increase repeated sampling trials beyond 3 to 6 (ablation)AdaGen-MaskGIT-L · ImageNet 256 (T=32)FID-50K: 1.81 -> 1.90Hurt
increase repeated sampling trials from 0 to 5 (ablation)AdaGen-DiT-XL · ImageNet 256 (T=16)FID-50K: 2.19 -> 1.91Improved
use FID as the reward for an adaptive policy (ablation)AdaGen-MaskGIT-L · ImageNet 256 (T=8)FID-50K: 2.56 -> 55.4 (Fail)Hurt
reduce inference steps (gain of AdaGen grows as steps drop)AdaGen-DiT-XL · ImageNet 256FID-50K: -1.12 at 16 steps, -2.36 at 8 steps, -4.40 at 4 stepsImproved

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