PulseAugur
实时 19:00:17
Dansk(DA) TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

新的令牌化方法提升大型推荐模型 · 2篇论文

两篇研究论文介绍了通过将各种信号转换为高效令牌表示来增强大型推荐模型的新颖方法。TokenMinds 专注于预训练离散用户令牌和密集嵌入以进行用户理解,并在 YouTube 上展示了其有效性。Token Factory 提出了一个将传统信号转换为“软令牌”的框架,能够高效地集成到基于 Transformer 的推荐模型中,并减少提示长度和计算开销。 AI

影响 这些方法旨在通过创建更有效的令牌表示来提高大型推荐模型的效率和性能。

排序理由 两篇 arXiv 论文介绍了将信号集成到大型推荐模型中的新颖方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的令牌化方法提升大型推荐模型 · 2篇论文

报道来源 [3]

  1. arXiv cs.LG TIER_1 Dansk(DA) · Qingyun Liu, Bo Yan, Yang Liu, Yuji Roh, Ekansh Sharma, Likang Yin, Emma Olowo, Min-hsuan Tsai, Yuxuan Li, Diego Uribe, Saksham Aggarwal, Siqi Wu, Yuan Hao, Vikas Kedigehalli, Lukasz Heldt, Lichan Hong, Li Wei, Xinyang Yi ·

    TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

    arXiv:2606.25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors. An emerging alternative for discrete user representation --…

  2. arXiv cs.IR (Information Retrieval) TIER_1 Dansk(DA) · Xinyang Yi ·

    TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

    User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors. An emerging alternative for discrete user representation -- using LLMs to generate text-based user tokens -- …

  3. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Xinyang Yi ·

    Token Factory:将多样化信号高效集成到大型推荐模型中

    Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional…