Vision Language Models (VLMs) have achieved remarkable success in a wide range of vision applications of increasing complexity and scales, yet choosing the right VLM model size involves a trade-off between response quality and cost. While smaller VLMs are cheaper to run, they typically produce responses only marginally better than random guessing on benchmarks such as MMMU. In this paper, we propose Cache of Thought (CoT), a master apprentice framework for collaborative inference between large and small VLMs. CoT manages high quality query results from large VLMs (master) in a cache, which are then selected via a novel multi modal retrieval and in-context learning to aid the performance of small VLMs (apprentice). We extensively evaluate CoT on various widely recognized and challenging general reasoning benchmarks, and show that CoT increases overall reasoning performance by up to 7.7% under the same budget, and specifically boosts the performance of apprentice VLMs by up to 36.6%. Our code is available at https://github.com/UIUC-MONET/Cache-of-Thoughts
@article{arxiv.2502.20587,
title = {Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning},
author = {Mingyuan Wu and Jize Jiang and Haozhen Zheng and Meitang Li and Zhaoheng Li and Beitong Tian and Bo Chen and Yongjoo Park and Minjia Zhang and Chengxiang Zhai and Klara Nahrstedt},
journal= {arXiv preprint arXiv:2502.20587},
year = {2025}
}
Comments
EMNLP 2025 Main Conference. Mingyuan, Jize, and Haozhen contributed equally, while Minjia, Chengxiang, and Klara advised equally