AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features

Markus Mueller, Kathrin Gruber, Dennis Fok

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools

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 a cascaded pipeline with distributional tree latents, data-dependent coupling and flow matching instead of joint CDTDCDTD · 12 tabular datasets, MNAR 10% missingdetection score: 0.518 -> 0.787Improved
add cascaded factorization (x_cat first, then x_num given x_cat) to CDTD (ablation)CDTD · 12 tabular datasetsdetection score: 0.518 -> 0.694Improved
add low-resolution latents z to cascaded CDTD without the flow matching changes (ablation)CDTD + cascade · 12 tabular datasetsdetection score: 0.694 -> 0.175Hurt
replace CDTD high-resolution model with flow matching (independent coupling, linear paths) (ablation)CDTD + latents z · 12 tabular datasetsdetection score: 0.175 -> 0.719Improved
add data-dependent coupling from z (ablation)flow matching high-resolution model · 12 tabular datasetsdetection score: 0.719 -> 0.786Improved
add learnable non-linear time schedules (paths) (ablation)flow matching with data-dependent coupling · 12 tabular datasetsdetection score: 0.786 -> 0.787No clear effect
use distributional tree encoder instead of Gaussian mixture model for z (ablation)TabCascade · 12 tabular datasetsdetection score: 0.479 -> 0.787Improved
use TabCascade instead of the best baselineCDTD · 12 tabular datasetsWasserstein distance (num): 0.009 -> 0.004Improved
use TabCascade instead of the best baselineCDTD · 12 tabular datasetsMLE: 0.039 -> 0.027Improved
use TabCascade instead of CDTDCDTD · 12 tabular datasetsMIA score: 0.958 -> 0.935Hurt
use TabCascade instead of CDTDCDTD · 12 tabular datasetsDCR share: 0.883 -> 0.890Hurt
use TabCascade instead of CDTD for categorical featuresCDTD · 12 tabular datasetsJSD (cat): 0.020 -> 0.018No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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