# Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach

arXiv: https://arxiv.org/abs/2605.20674 · HTML: https://mlsanity.com/paper/2605.20674/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 57 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature](https://mlsanity.com/paper/1505.00855/) (2015)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025)
- [PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones](https://mlsanity.com/paper/2007.00478/) (2020)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data](https://mlsanity.com/paper/2303.14080/) (2023)
- [CausalPFN: Amortized Causal Effect Estimation via In-Context Learning](https://mlsanity.com/paper/2506.07918/) (2025)
- [On the Dimensionality of Word Embedding](https://mlsanity.com/paper/1812.04224/) (2018)
- [A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities](https://mlsanity.com/paper/2502.17361/) (2025)
- [TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems](https://mlsanity.com/paper/2502.02527/) (2025)
- [TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data](https://mlsanity.com/paper/2407.07582/) (2024)
- [AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models](https://mlsanity.com/paper/2404.16233/) (2024)
- [Benchmarking Multimodal AutoML for Tabular Data with Text Fields](https://mlsanity.com/paper/2111.02705/) (2021)
- [Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning](https://mlsanity.com/paper/2507.14137/) (2025)
- [MATCH: Metadata-Aware Text Classification in A Large Hierarchy](https://mlsanity.com/paper/2102.07349/) (2021)
- [TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields](https://mlsanity.com/paper/2505.18125/) (2025)

## Abstract (arXiv)

We introduce CoMET, textitComposing Modality Encoders with Tabular foundation models, a simple yet highly competitive method for multimodal classification: pass each modality through a frozen pre-trained backbone, compress the resulting embeddings with PCA, and concatenate as input into a Tabular Foundation Model (TFM) for prediction. We show that PCA alone suffices to act as an adaptor yielding strong, robust performance across modalities. When the textttCLS tokens of the foundation model align poorly with downstream tasks, we propose PALPooling, a lightweight adaptive token pooler that consistently improves representation quality. By composing strong frozen representation learning backbones with TFMs, our approach achieves state-of-the-art results across diverse multimodal benchmarks without any training. On hierarchical tasks with large fine-grained class spaces, our approach enables fast and scalable classification, handling datasets with over 500,000 samples and 2,000 classes without any fine-tuning. Overall, our results show that the composition of foundation models is a simple, yet powerful, out-of-the-box solution for multimodal learning, challenging the necessity of complex, end-to-end training pipelines for new problems.