arXiv · cs.AI · Junyoung Kim, Woojoo Kim, Jaehyung Lim, Dongha Kim, Wonbin Kweon, Hwanjo Yu2026-11-03 13:00 · 9 小时前模型评分33

VLM2Rec：解决视觉语言模型在序列推荐中的模态坍缩问题

VLM2Rec: Resolving Modality Collapse in Vision-Language Models for Sequential Recommendation

导读

VLM2Rec 通过弱模态惩罚对比学习和跨模态关系拓扑正则化，缓解视觉语言模型（VLM，Vision-Language Model）在序列推荐中过度依赖文本、忽视视觉连续性的模态坍缩问题。

分类置信度

中 · 待人工复核

来源级别：媒体与个人

应用领域：零售与营销

事件类型：研究发布

证据摘录

“We propose VLM2Rec with two objectives: Weak-modality Penalized Contrastive Learning strengthens each user's weaker modality, and Cross-modal Relational Topology Regularization aligns each user's relative similarity structure over the same items across the two modality spaces.”

来源：arXiv · cs.AI · arxiv.org