AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Using maximal information auxiliary variables to improve synthetic data generation based on TabPFN foundation models

Elias Chaibub Neto

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Prediction-powered and conformal inference

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
replace direct TabPFN generation (JF) with MIAV auxiliary variablesTabPFN synthetic data generation · simulated, real OpenML-CC18 (36) and 7 baseline datasetsfidelity (KS, L2D, DT)Improved
weaken variable association strength (rho toward 0) for direct JF and FC strategies (ablation)JF and FC TabPFN generators · simulated correlated beta datamarginal distribution qualityHurt
use MIAV instead of SMOTEsynthetic data generator · real datasetsfidelityHurt
use MIAV instead of SMOTEsynthetic data generator · real datasetsprivacy (DCR, SDBRL, SSDID)Improved
use MIAV instead of DDPM, CTGAN, TVAE, ARF, BNsynthetic data generator · 7 real datasetsfidelityMixed
use MIAV instead of JF and FCsynthetic data generator · real datasetsprivacyHurt
build MIAV on TabICL instead of TabPFN (ablation)MIAV · 8 categorical OpenML-CC18 datasetssynthetic data qualityNo clear effect

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