AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

MultiTab: A Scalable Foundation for Multitask Learning on Tabular Data

Dimitrios Sinodinos, Jack Yi Wei, Narges Armanfard

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer neural operators for PDEs · 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 T-/->T masking (task tokens cannot attend to each other) to multi-token model (ablation)MultiTab-Net · Higgsmultitask gain Δm: 1.1182 -> 1.2337Improved
add T-/->T masking to multi-token model (ablation)MultiTab-Net · AliExpressmultitask gain Δm: 0.2579 -> 0.5512Improved
add T-/->T masking to multi-token model (ablation)MultiTab-Net · ACS Incomemultitask gain Δm: 0.0783 -> 0.1064Improved
use multiple task tokens instead of one shared token (no masking) (ablation)MultiTab-Net · Higgsmultitask gain Δm: -6.3491 -> 1.1182Improved
use multiple task tokens instead of one shared token (no masking) (ablation)MultiTab-Net · AliExpressmultitask gain Δm: 0.2669 -> 0.2579No clear effect
use multiple task tokens instead of one shared token (no masking) (ablation)MultiTab-Net · ACS Incomemultitask gain Δm: 0.0893 -> 0.0783No clear effect
add F-/->T masking to multi-token model (ablation)MultiTab-Net · Higgsmultitask gain Δm: 1.1182 -> 0.9626Hurt
add F-/->T masking to multi-token model (ablation)MultiTab-Net · AliExpressmultitask gain Δm: 0.2579 -> 0.3698Improved
add F-/->T masking to single-token model (ablation)MultiTab-Net · Higgsmultitask gain Δm: -6.3491 -> -12.5587Hurt
add F-/->T masking to single-token model (ablation)MultiTab-Net · AliExpressmultitask gain Δm: 0.2669 -> 0.1301Hurt
add F-/->T & T-/->T masking to multi-token model (ablation)MultiTab-Net · Higgsmultitask gain Δm: 1.1182 -> 1.0197Hurt
use MultiTab-Net instead of STEMMultiTab-Net vs STEM · Higgsmultitask gain Δm: 0.0571 -> 1.2337Improved

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