Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation

ArXi:2509.10468v2 Announce Type: replace-cross Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized for different objectives: semantic reconstruction during tokenizer pre