Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal caption-like text--image pairs and often fail to capture abstract or persona-driven attributes common in product recommendation applications (e.g., ``a gift for a mother who loves gardening''). In contrast, state-of-the-art vision--language models (vLLMs) can align text with images in a flexible manner, but their limited context window prevents them from directly handling retrieval over large catalogs. We propose a framework that distills the preference rankings of a powerful vLLM into an embedding-based system, transferring its nuanced alignment abilities while maintaining the inference-time scalability of an embedding-based approach. Experiments on persona-driven product recommendation tasks demonstrate that our method significantly outperforms existing embedding-based baselines, providing an efficient solution for personalized text--image retrieval.
@article{arxiv.2510.12014,
title = {Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval},
author = {Eric He and Akash Gupta and Adian Liusie and Vatsal Raina and Piotr Molenda and Shirom Chabra and Vyas Raina},
journal= {arXiv preprint arXiv:2510.12014},
year = {2025}
}