AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

TFTF: Training-Free Targeted Flow for Conditional Sampling

Qianqian Qu, Jun S. Liu

ICML 2026 · Image generation › Fast diffusion sampling · approach: Guidance and alignment for flow matching · 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 intermediate SMC resampling to importance sampling (ablation)TFTF · CIFAR-10 automobile class, K=16ESS: 1.37/16 -> 16.00/16Improved
increase stochasticity scale alpha(t) from 1/t to larger values (ablation)TFTF · MNIST class-conditionalintra-batch diversity and ACC_EMixed
increase particle count K (ablation)TFTF · MNIST class-conditionalACC_EImproved
use TFTF instead of Twisted Diffusion SamplerMNIST class-conditional · MNISTACC_E and intra-batch diversityImproved
use TFTF instead of FlowChefflow matching conditional sampling · MNISTACC_E: 23.57% -> 97.12%Improved
use TFTF instead of FlowChefflow matching conditional sampling · CIFAR-10ACC_E: 50.13% -> 92.82%Improved
use TFTF instead of FMPSflow matching conditional sampling · CelebA-HQ text-to-imageACC_E: 68.69% -> 80.99%Improved
use TFTF instead of FMPSflow matching conditional sampling · CelebA-HQ text-to-imageCLIP_L: 0.307 -> 0.295Hurt
resampling introduces inter-particle correlationTFTF · batch samplesvisual diversity within batchHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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