arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.23643cs.AI
收藏

TailorMind: 面向偏好对齐的多模态内容生成

TailorMind: Towards Preference-Aligned Multimodal Content Generation

South China University of Technology(华南理工大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳))

Hengji Zhou, Ye Liu, Yufeng Liu, Si Wu, Lianghao Xia, Liqiang Nie

AI总结:

提出TailorMind框架,通过超图协同过滤和文本梯度下降建模用户偏好,结合检索增强风格控制和跨模态一致性反射,实现无候选池的个性化多模态内容生成,在TailorBench上优于基线。

摘要:

个性化内容系统依赖于可用的用户生成内容(UGC),当合适的内容缺失、延迟或创建成本高昂时,系统会陷入困境。尽管多模态生成器可以按需合成内容,但如何将行为痕迹转化为生成就绪的偏好仍未被充分探索。我们研究个性化多模态内容生成:在没有现有项目池或等待匹配UGC的情况下,创建用户定制的多模态内容。我们提出TailorMind,将协同偏好建模与可控多模态生成联系起来。TailorMind通过超图协同过滤丰富稀疏的用户历史,并利用排序误差反馈和文本梯度下降优化文本画像。检索增强风格控制将输出锚定在真实的UGC模式中,而跨模态一致性反射减少了语义漂移。我们构建了TailorBench,一个来自三个主流平台的基准,从五个维度进行评估:连贯性、新颖性、美学性、幻觉性、画像性。实验表明,TailorMind在连贯性上达到或超过代表性生成基线和真实UGC,提高了新颖性和美学质量,展示了优于检索可用内容或可比UGC的优势,同时在重排序中实现了高达29%的召回率提升。我们的代码发布在:this https URL。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑