Preprint
Aug 2026
Rethinking Item Tokenization in Generative Recommenders: From Fixed Atoms to Semantic Subwords
In generative recommender systems, items are typically tokenized into fixed-length semantic ID sequences for autoregressive next-item prediction. However, for user-context modeling, this fine-grained representation triggers Intra-item Attention Overload: excessive attention is spent on low-level intra-item dependencies...
Xinrui Miao, Mingjia Yin, Jiaqing Zhang et al.
· 0 citations