个性化内容系统依赖于可用的 UGC，当缺乏合适的内容, 延迟, 或创建成本高昂时，就会陷入困境。尽管多模式生成器可以按需合成内容,，但如何将行为痕迹转化为可生成的偏好仍然尚未得到充分探索。我们研究个性化多模式内容生成:，创建用户定制的多模式内容，无需现有项目池或等待匹配的 UGC。我们提出 TailorMind, 将协作偏好建模与可控多模式生成联系起来。 TailorMind 通过超图协同过滤丰富稀疏的用户历史，并通过排名错误反馈和文本梯度下降优化文本配置文件。检索增强的风格控制将输出置于真实的 UGC 模式, 中，而跨模式内聚反射则减少了语义漂移。我们从三个主流平台构建TailorBench,基准，从五个维度:连贯性,新颖性,审美,幻觉,分析。实验表明，TailorMind 实现了有竞争力或更强的连贯性,，与代表性生成基线和真实 UGC, 相比，提高了新颖性和美观质量，展示了相对于检索可用内容或可比 UGC, 的优势，同时在重新排名中实现了高达 29% 的召回增益。我们的代码在: 这个 https URL 上发布。
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: this https URL.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)