AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

No Need to Train Your RDB Foundation Model

Linjie Xu, Yanlin Zhang, Quan Gan, Minjie Wang, David Wipf

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 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 cross-column dense encoder mixing in front of the ICL decoder with many uninformative columns (ablation)TabPFNv2 ICL decoder · synthetic classificationaccuracyHurt
add cross-column dense encoder when added columns are informative (ablation)TabPFNv2 ICL decoder · synthetic classificationaccuracyNo clear effect
swap dense parameterized encoder for JUICE-style parameter-free encoder under ICLKumoRFM vs RDBLearn · RelBench-v1AUC differenceImproved
use JUICE encoder with supervised head instead of dense encoderRelGT vs AutoGluon on JUICE · RelBench-v1AUC differenceHurt
vary base tabular model (TabPFN-v2, v2.5, LimiX) and hops H in {2,3} (ablation)RDBLearn · RelBench-v1 classificationAUCNo clear effect
replace random GNN encoder with JUICE (no cross-column mixing) (ablation)RandGNN · RelBench-v1 classificationAUCImproved
use RDBLearn instead of RandGNN4DBInfer Retailrocket CVR · Retailrocket CVRAUC: 0.6621 -> 0.8469Improved
use RDBLearn instead of RandGNN4DBInfer Outbrain CTR-100K · Outbrain CTR-100KAUC: 0.4929 -> 0.5447Improved
train RT without pre-training on each test RDBRT · RelBench-v1 classificationAUC: 70.1 -> 66.7Hurt

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