{"ID":2856628,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12014","arxiv_id":"2510.12014","title":"Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval","abstract":"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.","short_abstract":"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 attr...","url_abs":"https://arxiv.org/abs/2510.12014","url_pdf":"https://arxiv.org/pdf/2510.12014v1","authors":"[\"Eric He\",\"Akash Gupta\",\"Adian Liusie\",\"Vatsal Raina\",\"Piotr Molenda\",\"Shirom Chabra\",\"Vyas Raina\"]","published":"2025-10-13T23:30:07Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}