mlsanityData to 14 Oct 2026

The Importance of Encoder Choice:A Tabular-Image Study

arXiv 2607.07756 ↗First posted 8 Jul 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multimodal learning usually requires a dedicated encoder per modality. When a tabular modality is involved, prior work has been mostly using a plain MLP as the encoder. Yet if it were a strong encoder, the tabular domain would not be ``the last unconquered castle for deep learning''. This study evaluates state-of-the-art tabular models as encoders in the image-tabular setting for the first time. An obstacle stands out. In-Context Learning models, among the best performing methods in the tabular domain, require labels to process instances, making it non-trivial to embed training and test instances the same way. We addressed this problem across multiple models of this family. With this study, we would like to highlight the importance of encoder factor in the multimodal learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

34 of 48 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  4. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  5. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  6. 2021Tabular Data: Deep Learning is Not All You Needcited by 535
  7. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  8. 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Datacited by 289
  9. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 199
  10. 2025TabArena: A Living Benchmark for Machine Learning on Tabular Datacited by 176
  11. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  12. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
22 more
  1. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  2. 2026TabICLv2: A better, faster, scalable, and open tabular foundation modelcited by 144
  3. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  4. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  5. 2024TabDPT: Scaling Tabular Foundation Models on Real Datacited by 113
  6. 2024TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensemblingcited by 113
  7. 2020COVID-19 Image Data Collection: Prospective Predictions Are the Futurecited by 100
  8. 2023XTab: Cross-table Pretraining for Tabular Transformerscited by 81
  9. 2023Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Datacited by 69
  10. 2024TALENT: A Tabular Analytics and Learning Toolboxcited by 52
  11. 2022Revisiting Pretraining Objectives for Tabular Deep Learningcited by 43
  12. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  13. 2024A Closer Look at Deep Learning Methods on Tabular Datasetscited by 41
  14. 2021ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Geneticscited by 36
  15. 2024TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Datacited by 32
  16. 2023UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Sciencecited by 29
  17. 2025Table Foundation Models: on knowledge pre-training for tabular learningcited by 19
  18. 2021DVM-CAR: A large-scale automotive dataset for visual marketing research and applicationscited by 17
  19. 2024HyperFusion: A Hypernetwork Approach to Multimodal Integration of Tabular and Medical Imaging Data for Predictive Modelingcited by 15
  20. 2023Multimodal Contrastive Learning and Tabular Attention for Automated Alzheimer's Disease Predictioncited by 12
  21. 2024Bag of Tricks for Multimodal AutoML with Image, Text, and Tabular Datacited by 7
  22. 2025Table as a Modality for Large Language Modelscited by 7

Built on by

Not cited yet.