AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Test-Time Anchoring for Discrete Diffusion Posterior Sampling

Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan, Constantine Caramanis, Sanjay Shakkottai, Ira Kemelmacher-Shlizerman

ICML 2026 · Image generation › Fast diffusion sampling · approach: Discrete diffusion solvers · 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
use APS instead of G2D2discrete diffusion sampler · FFHQ SR (4x)LPIPS: APS reduces LPIPS by 13.65%Improved
use APS instead of G2D2discrete diffusion sampler · FFHQ SR (4x)PSNR: improves PSNR by 2.11%Improved
use APS instead of G2D2discrete diffusion sampler · FFHQ Gaussian deblurLPIPS: lowers LPIPS by 3.83%Improved
use APS instead of G2D2discrete diffusion sampler · FFHQ Gaussian deblurPSNR: raises PSNR by 5.88%Improved
use large-resolution variant APS-L (1024x1024 upsampled) instead of G2D2APS · FFHQLPIPS: up to a 31.36% gain over G2D2Improved
use APS instead of G2D2discrete diffusion sampler · ImageNet SR (4x)LPIPS: reduces LPIPS by 7.16%Improved
use APS instead of G2D2discrete diffusion sampler · ImageNet SR (4x)PSNR: improves PSNR by 4.74%Improved
use APS instead of G2D2discrete diffusion sampler · ImageNet Gaussian deblurPSNR: improves PSNR by 8.81%Improved
use APS-L instead of G2D2APS · ImageNetLPIPS: improves LPIPS by up to 35.82%Improved
add APS guidance to MMaDAMMaDA · Reference-based stylizationImageReward: 0.48 -> 0.63Improved
add APS guidance to MMaDAMMaDA · Reference-based stylizationDINO: 0.32 -> 0.41Improved
add APS with Qwen3-0.6B reward model to Dream-7B-InstructDream-7B-Instruct · Question answering (20 questions)Oracle judge score: 3.7523 -> 4.5775Improved

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