Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.29287 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910278464045056 |
|---|---|
| author | Zhao, Jinghan Jin, Wenwei Li, Anqi Tong, Jintao Mo, Luya Li, Jiawei Li, Bin Hu, Yao |
| author_facet | Zhao, Jinghan Jin, Wenwei Li, Anqi Tong, Jintao Mo, Luya Li, Jiawei Li, Bin Hu, Yao |
| contents | Item-to-Item (I2I) retrieval is a fundamental part of modern content platforms, supporting critical industrial workflows from recommendation engines to content auditing. While multimodal embedding methods have advanced general retrieval, they often falter in I2I scenarios due to the challenges of balancing global content representation with fine-grained local retrieval, the systemic inefficiency of decoupled embedding-and-ranking pipelines, and the inherent trade-offs between model precision and serving latency. To solve these issues, we propose \textbf{UniNote}, a unified embedding model designed for industrial I2I retrieval. Tailored retrieval strategies are introduced to support representation learning over complex, multimodal content at varying granularities. To operationalize these strategies, UniNote employs a two-stage training paradigm: the first stage leverages contrastive SFT to establish robust base embeddings, while the second stage refines ranking quality through a reinforcement learning (RL) process that aligns the model with content relevance. Our results show that UniNote achieves SOTA performance across diverse I2I tasks. Deployed at Xiaohongshu and integrated with Matryoshka Representation Learning (MRL), UniNote achieved significant improvements in retrieval quality and cost efficiency in large-scale applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29287 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniNote: A Unified Embedding Model for Multimodal Representation and Ranking Zhao, Jinghan Jin, Wenwei Li, Anqi Tong, Jintao Mo, Luya Li, Jiawei Li, Bin Hu, Yao Information Retrieval Computer Vision and Pattern Recognition Item-to-Item (I2I) retrieval is a fundamental part of modern content platforms, supporting critical industrial workflows from recommendation engines to content auditing. While multimodal embedding methods have advanced general retrieval, they often falter in I2I scenarios due to the challenges of balancing global content representation with fine-grained local retrieval, the systemic inefficiency of decoupled embedding-and-ranking pipelines, and the inherent trade-offs between model precision and serving latency. To solve these issues, we propose \textbf{UniNote}, a unified embedding model designed for industrial I2I retrieval. Tailored retrieval strategies are introduced to support representation learning over complex, multimodal content at varying granularities. To operationalize these strategies, UniNote employs a two-stage training paradigm: the first stage leverages contrastive SFT to establish robust base embeddings, while the second stage refines ranking quality through a reinforcement learning (RL) process that aligns the model with content relevance. Our results show that UniNote achieves SOTA performance across diverse I2I tasks. Deployed at Xiaohongshu and integrated with Matryoshka Representation Learning (MRL), UniNote achieved significant improvements in retrieval quality and cost efficiency in large-scale applications. |
| title | UniNote: A Unified Embedding Model for Multimodal Representation and Ranking |
| topic | Information Retrieval Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.29287 |