TailorMind: Towards Preference-Aligned Multimodal Content Generation
2026-06-22 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address a problem in personalized content creation when there isn't enough existing user content to use. They introduce TailorMind, a system that combines user preference modeling with AI-generated multimodal content (like images and text) tailored to individual users. TailorMind improves user profiles and controls the style of generated content, making the results more coherent and appealing. They also create TailorBench, a benchmark to test such systems, and show that TailorMind outperforms other methods in several quality measures.
personalized contentuser-generated content (UGC)multimodal generationcollaborative filteringhypergraphpreference modelingretrieval augmentationsemantic driftcontent benchmarkingreranking
Authors
Hengji Zhou, Ye Liu, Yufeng Liu, Si Wu, Lianghao Xia, Liqiang Nie
Abstract
Personalized content systems depend on available UGC and struggle when suitable content is absent, delayed, or costly to create. Although multimodal generators can synthesize content on demand, how to translate behavioral traces into generation-ready preferences remains underexplored. We study personalized multimodal content generation: creating user-tailored multimodal content without existing item pools or waiting for matching UGC. We propose TailorMind, linking collaborative preference modeling with controllable multimodal generation. TailorMind enriches sparse user histories via hypergraph collaborative filtering and optimizes textual profiles with ranking-error feedback and textual gradient descent. Retrieval-augmented style control grounds outputs in authentic UGC patterns, while cross-modal cohesion reflection reduces semantic drift. We construct TailorBench, a benchmark from three mainstream platforms evaluated along five dimensions: coherence, novelty, aesthetic, hallucination, profiling. Experiments show that TailorMind achieves competitive or stronger coherence, improves novelty and aesthetic quality over representative generation baselines and ground-truth UGC, demonstrating advantages over retrieving available content or comparable UGC, while achieving up to 29% Recall gains in reranking. Our code is released at: https://github.com/iLearn-Lab/TailorMind.