Preprint
Oct 2026
UniSGR-V2: Stepwise Target-Side Feature Anticipation and Crossing for Generative Recommendation
Semantic-ID-based generative recommendation unifies retrieval and ranking through autoregressive decoding but differs structurally from discriminative models, which can directly access rich target-item side features. The attributes are compressed into a finite codebook during quantization, while the target item remains...
Jun Yang, Jia-Siang Chen, Jia-Wei Sun et al.
· 0 citations