AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction

Soochul Park, Yeon Ju Lee

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 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 second-order corrector to first-order predictor (p1 -> p1c2) (ablation)Dual-Solver · DiT, NFE=3cross-entropy loss: 0.667 -> 0.574Improved
use second-order predictor with corrector (p2c2) instead of p1c2 (ablation)Dual-Solver · DiT, NFE=3cross-entropy loss: 0.574 -> 5.009Hurt
make all of gamma, tau, kappa learnable instead of fixing gamma=-1 (ablation)Dual-Solver · DiT, NFE=5cross-entropy loss: 7.676 -> 0.197Improved
make all parameters learnable instead of kappa=0 (remove second-order residual) (ablation)Dual-Solver · DiT, NFE=3cross-entropy loss: 0.944 -> 0.574Improved
make all parameters learnable instead of fixing or sharing them (ablation)Dual-Solver · DiT, NFE=9cross-entropy loss: 0.173 vs 0.169 (tau,kappa shared)Mixed
use log1p domain change (Type 2) instead of linear/log interpolation (Type 1) (ablation)Dual-Solver · DiT, NFE=9FID: 3.64 -> 2.67Improved
use log1p domain change (Type 2) instead of Type 1 (ablation)Dual-Solver · DiT, NFE=3FID: 23.38 -> 24.91Hurt
learn with hard-label classification instead of sample regression (ablation)Dual-Solver · DiT, NFE=3FID: 107.13 -> 24.91Improved
learn with hard-label classification instead of feature regression (VGG) (ablation)Dual-Solver · DiT, NFE=5FID: 5.48 -> 3.52Improved
learn with hard labels instead of soft labels (ablation)Dual-Solver · DiT, NFE=5FID: 4.90 -> 3.52Improved
use trajectory-regression objective (Dual-Solver-R) instead of classification (Dual-Solver-C) (ablation)Dual-Solver · GM-DiT, NFE=9FID: 2.60 -> 2.32 (R better at NFE 8-9)Hurt
replace DS-Solver with Dual-SolverDiT · ImageNet, NFE=3FID: 67.31 -> 24.91Improved

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