3 papers
cs.IR2026
LazFormer: Scaling Transformers for Industrial Recommendation via Transferable Generative Pre-training
Xiaodong Li, Alin Fan, Mingyang Li +7
Transformers have shown promising performance in LLMs due to their outstanding scalability, several studies have investigated the scalability of Transformers for industrial recomme…
cs.IR2026
MIMA: Multi-Interest Recommendation via Multi-Positive Exclusive Assignment
Xingyuan Mao, Alin Fan, Shichao Nie +4
Multi-interest recommendation represents each user with multiple interest vectors for fine-grained candidate matching, yet it often suffers from interest collapse, where the learne…
cs.IR2025
Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction
Alin Fan, Hanqing Li, Sihan Lu +2
Modern industrial recommendation systems improve recommendation performance by integrating multimodal representations from pre-trained models into ID-based Click-Through Rate (CTR)…