IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu

Abstract:Content-driven platforms such as Xiaohongshu often leverage click-through rate (CTR) prediction models for recommendation. However, these models depend heavily on item ID embeddings, which perform poorly in item cold-start settings. In this paper, we present IDProxy, a production-scale system developed at Xiaohongshu to address this challenge. IDProxy leverages multimodal large language models (MLLMs) to generate proxy embeddings from rich content signals, enabling CTR prediction for new items in the absence of usage data. Through a lightweight coarse-to-fine mechanism, these proxies are aligned with the ID embedding space and trained end-to-end with the ranking model, allowing seamless integration into production-facing pipelines. Extensive offline and online experiments demonstrate the effectiveness of the method, which has been deployed in 2025 in Xiaohongshu's Content Feed and Display Ads features, reaching hundreds of millions of users daily.

Information Retrieval (cs.IR); Machine Learning (cs.LG)

arXiv:2603.01590 [cs.IR]

(or arXiv:2603.01590v2 [cs.IR] for this version)

https://doi.org/10.48550/arXiv.2603.01590 Focus to learn more arXiv-issued DOI via DataCite

https://doi.org/10.1145/3773078.3831874 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.