Researchers at Xiaohongshu have developed IntentFlow, a novel real-time multimodal search system designed to improve search relevance for image-text queries. Unlike traditional methods that rely solely on visual or topical similarity, IntentFlow explicitly models user retrieval intent using a hierarchical taxonomy. This approach guides data construction, representation learning, and reranking, leading to significant improvements in search engagement. An A/B test on the Xiaohongshu platform showed IntentFlow achieved substantial gains in click-through rates and user time spent on search results pages, while maintaining industrial-scale latency. AI
IMPACT Enhances search relevance for multimodal queries, potentially improving user experience and engagement in content platforms.
RANK_REASON The item is a research paper detailing a new system for multimodal search, not a direct product release from a major AI lab. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- IntentFlow
- Litmaps
- ScienceCast
- scite Smart Citations
- Xiaohongshu
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →