{"ID":5552800,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-03T19:58:09.389792377Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00125","arxiv_id":"2607.00125","title":"Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners","abstract":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prompted to decide whether the two images depict the same class. The logit corresponding to an affirmative response is then used as a similarity score to assign the query image to the most likely class. While this already yields good results, we show that providing additional high-level information, such as the data domain, to the model further improves performance. Our evaluation provides an extensive analysis of various inference variants on a suite of twelve datasets, six established and six newly curated few-shot benchmarks spanning across diverse domains. The results show that the proposed simple decomposition technique can turn off-the-shelf MLLMs into powerful few-shot learners, significantly outperforming current state-of-the-art few-shot methods on both standard and novel domains. Code is available at https://github.com/yunhanwang1105/DeCoDe.","short_abstract":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-sh...","url_abs":"https://arxiv.org/abs/2607.00125","url_pdf":"https://arxiv.org/pdf/2607.00125v1","authors":"[\"Yunhan Wang\",\"Eshika Khandelwal\",\"Edson Araujo\",\"Walid Bousselham\",\"Nina Shvetsova\",\"Hilde Kuehne\"]","published":"2026-06-30T20:00:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":613860,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-02T01:54:51.863792489Z","DeletedAt":null,"paper_id":5552800,"paper_url":"https://arxiv.org/abs/2607.00125","paper_title":"Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners","repo_url":"https://github.com/yunhanwang1105/DeCoDe","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}