AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning

Wall Kim, Chaeyoung Song, Hanul Kim

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 7 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 image features to fine-tuned TabPFNTabPFN · PAD-UFES-20accuracy (%): 82.17 -> 85.22Improved
add image features to TabPFN on CBIS-DDSM MassTabPFN · CBIS-DDSM Massaccuracy (%): 71.27 -> 74.53Improved
MMPFN vs text-specialized AutoGluon on ClothAutoGluon · Clothaccuracy (%): 72.07 -> 66.26Hurt
add text to TabPFN on ClothTabPFN · Clothaccuracy (%): 55.07 -> 66.26Improved
replace single-head linear projector with multi-head gated MLP (MGM) (ablation)MMPFN · 9-dataset averageaccuracy (%): 53.86 -> 57.37Improved
replace MGM with mixture-of-experts heads (ablation)MMPFN · 9-dataset averageaccuracy (%): 57.37 -> 53.23Hurt
add GLU gating to multi-head MLP (ablation)MMPFN · 9-dataset averageaccuracy (%): 55.81 -> 57.37Improved
replace FiLM with cross-attention pooler (CAP) (ablation)MMPFN · 9-dataset averageaccuracy (%): 55.48 -> 57.37Improved
add CAP at large token count (N=128) (ablation)MGM · PAD-UFES-20accuracy (%): 83.91 -> 84.59Improved
add CAP when token count rises to 4x32 (ablation)MGM · Clothaccuracy (%): 61.76 -> 64.22Improved
increase number of non-tabular tokens with tabular inputs, no CAP (ablation)MMPFN · PAD-UFES-20accuracy (%)Hurt
train on only 10% of data vs TIPTIP · PAD-UFES-20accuracy (%): 70.44 -> 72.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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