collaborators

5 papers

cs.LG2026

MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms

Jinqi Wu, Sishuo Chen, Zhangming Chan +9

Multi-attribution learning (MAL), which enhances model performance by learning from conversion labels yielded by multiple attribution mechanisms, has emerged as a promising learnin…

cs.IR2026

EST: Towards Efficient Scaling Laws in Click-Through Rate Prediction via Unified Modeling

Mingyang Liu, Yong Bai, Zhangming Chan +5

Efficiently scaling industrial Click-Through Rate (CTR) prediction has recently attracted significant research attention. Existing approaches typically employ early aggregation of…

cs.IR2025

VQL: An End-to-End Context-Aware Vector Quantization Attention for Ultra-Long User Behavior Modeling

Kaiyuan Li, Yongxiang Tang, Yanhua Cheng +5

In large-scale recommender systems, ultra-long user behavior sequences encode rich signals of evolving interests. Extending sequence length generally improves accuracy, but directl…

cs.IR2025

CHIME: A Compressive Framework for Holistic Interest Modeling

Yong Bai, Rui Xiang, Kaiyuan Li +5

Modeling holistic user interests is important for improving recommendation systems but is challenged by high computational cost and difficulty in handling diverse information with…

cs.IR2025

BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation

Kaiyuan Li, Rui Xiang, Yong Bai +5

Multi-modal sequential recommendation systems leverage auxiliary signals (e.g., text, images) to alleviate data sparsity in user-item interactions. While recent methods exploit lar…