9 papers
Taming the Long Tail: Denoising Collaborative Information for Robust Semantic ID Generation
Yi Xu, Moyu Zhang, Chaofan Fan +5
Item IDs form the backbone of industrial recommender systems, but suffer from representation instability and poor long-tail generalization in large, dynamic item corpora. Semantic…
Learning to Reflect and Correct: Towards Better Decoding Trajectories for Large-Scale Generative Recommendation
Haibo Xing, Hao Deng, Lingyu Mu +4
Generative Recommendation (GR) has become a promising paradigm for large-scale recommendation systems. However, existing GR models typically perform single-pass decoding without ex…
REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems
Haibo Xing, Hao Deng, Yucheng Mao +9
Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction,…
Masked Diffusion Generative Recommendation
Lingyu Mu, Hao Deng, Haibo Xing +4
Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decodi…
STORE: Semantic Tokenization, Orthogonal Rotation and Efficient Attention for Scaling Up Ranking Models
Yi Xu, Chaofan Fan, Jinxin Hu +3
Ranking models have become an important part of modern personalized recommendation systems. However, significant challenges persist in handling high-cardinality, heterogeneous, and…
MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Yi Xu, Moyu Zhang, Chenxuan Li +7
Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiti…