Preprint
Aug 2026
Tlow: Flow-based Item Tokenizer for Recommendation
This work proposes a funderline-based item-based item tokenizer (Tlow) to transform raw semantic embeddings into a latent space where embeddings conform to a unified standard normal distribution, achieving dual advantages of dimensional independence and distributional simplicity.
Nian Li, Chonggang Song, Jing-Tao Ding et al.
· 0 citations