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

arXiv: https://arxiv.org/abs/2603.01590 · HTML: https://mlsanity.com/paper/2603.01590/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Linguistic Knowledge and Transferability of Contextual Representations](https://mlsanity.com/paper/1903.08855/) (2019)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Layer by Layer: Uncovering Hidden Representations in Language Models](https://mlsanity.com/paper/2502.02013/) (2025)
- [VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback](https://mlsanity.com/paper/1510.01784/) (2015)
- [Deep Learning based Recommender System: A Survey and New Perspectives](https://mlsanity.com/paper/1707.07435/) (2017)
- [Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1803.02349/) (2018)
- [Contrastive Learning for Cold-Start Recommendation](https://mlsanity.com/paper/2107.05315/) (2021)
- [Large Language Models for Generative Recommendation: A Survey and Visionary Discussions](https://mlsanity.com/paper/2309.01157/) (2023)
- [Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings](https://mlsanity.com/paper/1904.11547/) (2019)
- [NoteLLM-2: Multimodal Large Representation Models for Recommendation](https://mlsanity.com/paper/2405.16789/) (2024)
- [Deep Learning for Click-Through Rate Estimation](https://mlsanity.com/paper/2104.10584/) (2021)
- [Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Models](https://mlsanity.com/paper/2209.06053/) (2022)
- [Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2408.09698/) (2024)
- [Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights](https://mlsanity.com/paper/2407.19467/) (2024)
- [A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps](https://mlsanity.com/paper/2106.03819/) (2021)
- [Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap](https://mlsanity.com/paper/2501.01945/) (2025)
- [Large Language Models as Data Augmenters for Cold-Start Item Recommendation](https://mlsanity.com/paper/2402.11724/) (2024)
- [Contrastive Collaborative Filtering for Cold-Start Item Recommendation](https://mlsanity.com/paper/2302.02151/) (2023)
- [Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework](https://mlsanity.com/paper/2201.10980/) (2022)
- [LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations](https://mlsanity.com/paper/2404.00702/) (2024)
- [Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders](https://mlsanity.com/paper/2108.01053/) (2021)
- [Large Language Model Simulator for Cold-Start Recommendation](https://mlsanity.com/paper/2402.09176/) (2024)
- [A Survey on Large Language Models in Multimodal Recommender Systems](https://mlsanity.com/paper/2505.09777/) (2025)
- [MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding](https://mlsanity.com/paper/2508.11999/) (2025)
- [Test Time Embedding Normalization for Popularity Bias Mitigation](https://mlsanity.com/paper/2308.11288/) (2023)
- [Wasserstein Collaborative Filtering for Item Cold-start Recommendation](https://mlsanity.com/paper/1909.04266/) (2019)

## Built on by (most cited first, 2 of 2)

- [Music Playlist Captioning at Scale with Large Language Models](https://mlsanity.com/paper/2606.22460/) (2026)
- [Privacy in Personalized AI Is a System Property, Not Just a Model Property](https://mlsanity.com/paper/2609.38289/) (2026)

## Abstract (arXiv)

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.