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

• URL: http://arxiv.org/abs/2605.20674v1
• Date: Wed, 20 May 2026 03:43:19 GMT
• Title: Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach
• Abstract summary: We introduce CoMET, textittextbfComposing textbfModality textbfEncoders with textbfTabular foundation models.<n>Our approach achieves state-of-the-art results across diverse multimodal benchmarks without any training.
• Score: 10.561568484274044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce CoMET, \textit{\textbf{C}omposing \textbf{M}odality \textbf{E}ncoders with \textbf{T}abular 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 \texttt{CLS} tokens of the foundation model align poorly with downstream tasks, we propose \textbf{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.

Related papers

• Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing [18.589015768150578]
  Mixture of Probes (MoP) is a novel framework that disentangles modality-specific and modality-general signals within the Multimodal Large Language Models (MLLMs)<n>MoP consistently outperforms strong MLLM baselines, achieving up to 65% relative improvement.
  arXiv  Detail & Related papers  (2026-07-09T18:00:47Z)
• SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning [3.9890357781493595]
  We introduce the emphSubmodular Modality Aligner (SMA), which treats multiple augmentations and descriptions of an entity as a set, leveraging multiple descriptions of the data to capture richer cross-modal structure.<n>We evaluate SMA on 14 zero-shot classification and retrieval tasks from the CLIP benchmark and demonstrate consistent gains in the low-data regime.
  arXiv  Detail & Related papers  (2026-05-13T01:36:43Z)
• Fine-tuning MLLMs Without Forgetting Is Easier Than You Think [72.59321247529975]
  We design a 2x2 experimental framework to assess model performance across in-distribution and out-of-distribution image and text inputs.<n>Our results show that appropriate regularization, such as constraining the number of trainable parameters or adopting a low learning rate, effectively prevents forgetting when dealing with out-of-distribution images.<n>We attribute this forgetting as task-specific overfitting and address this issue by introducing a data-hybrid training strategy.
  arXiv  Detail & Related papers  (2026-03-15T17:16:19Z)
• TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics [56.073642366268764]
  TokaMind is an open-source foundation model framework for fusion plasma modeling.<n>It is trained on heterogeneous tokamak diagnostics from the publicly available MAST dataset.<n>We evaluate TokaMind on the recently introduced MAST benchmark TokaMark.
  arXiv  Detail & Related papers  (2026-02-16T12:26:07Z)
• Fine-Grained Model Merging via Modular Expert Recombination [33.253051407398836]
  We propose MERGE, a method that enables component-wise model merging and input-aware, on-demand module recombination at inference.<n> MERGE formulates component-wise merging as a bi-objective optimization problem that balances cross-task performance and storage efficiency.<n>We show that MERGE consistently outperforms strong baselines and generalizes effectively.
  arXiv  Detail & Related papers  (2026-02-06T09:55:56Z)
• Bagging-Based Model Merging for Robust General Text Embeddings [73.51674133699196]
  General-purpose text embedding models underpin a wide range of NLP and information retrieval applications.<n>We present a systematic study of multi-task training for text embeddings from two perspectives: data scheduling and model merging.<n>We propose Bagging-based rObust mOdel Merging (BOOM), which trains multiple embedding models on sampled subsets and merges them into a single model.
  arXiv  Detail & Related papers  (2026-02-05T15:45:08Z)
• MultiModal Fine-tuning with Synthetic Captions [9.572235167281686]
  We propose a novel approach that transforms unimodal datasets into multimodal ones using Multimodal Large Language Models (MLLMs)<n>Our method employs carefully designed prompts incorporating class labels and domain context to produce high-quality captions for classification tasks.<n>Our work establishes a new paradigm for dataset enhancement that effectively bridges the gap between multimodal pre-training and fine-tuning.
  arXiv  Detail & Related papers  (2026-01-29T09:03:45Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models [53.03670032402846]
  We address the task of table image to code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs.<n>A central challenge of this task lies in accurately handling complex tables -- those with large sizes, deeply nested structures, and semantically rich or irregular cell content.<n>We propose a reinforced multimodal large language model (MLLM) framework, where a pre-trained MLLM is fine-tuned on a large-scale table-to-La dataset.
  arXiv  Detail & Related papers  (2025-09-22T11:13:48Z)
• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You [3.3384874808567173]
  Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment, zero-shot classification and cross-modal retrieval.<n>Existing models typically rely on millions of paired samples, which are expensive or infeasible to obtain in domains.<n>We introduce an effective regularization technique that preserves the latent space of unimodal layers.<n>These two components can be readily incorporated into existing alignment methods, yielding substantial gains across 24 zero-shot image classification and retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-06-20T10:32:54Z)
• Leveraging Foundation Models for Multi-modal Federated Learning with Incomplete Modality [41.79433449873368]
  We propose a novel multi-modal federated learning method, Federated Multi-modal contrastiVe training with Pre-trained completion (FedMVP) FedMVP integrates the large-scale pre-trained models to enhance the federated training. We demonstrate that the model achieves superior performance over two real-world image-text classification datasets.
  arXiv  Detail & Related papers  (2024-06-16T19:18:06Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.