Universal Item Tokenization for Transferable Generative Recommendation
Abstract
Recently, generative recommendation has emerged as a promising paradigm, attracting significant research attention. The basic framework involves an item tokenizer, which represents each item as a sequence of codes serving as its identifier, and a generative recommender that predicts the next item by autoregressively generating the target item identifier. However, in existing methods, both the tokenizer and the recommender are typically domain-specific, limiting their ability for effective transfer or adaptation to new domains.
Fields of Study & Subjects
Multimodal Machine Learning Applications
Generative Adversarial Networks and Image Synthesis
Topic Modeling
Publication details
- Journal / source
- Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Pages
- 2509–2520
- Publication date
- 10 July 2026
- Language
- EN