11 papers
TWICE: Two-Clock, Two-Window Learning for Long-Horizon Conversion Prediction in Online Advertising
Kaiyuan Li, Kun Wang, Zhongbo Wang +4
Long-horizon conversion prediction under delayed feedback creates a two-clock, two-window learning problem in online advertising. A short base observation window releases recent cl…
ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate
Zijun Xie, Yuyang You, Yongzhi Li +8
Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their…
FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
Xikai Zhang, Yongzhi Li, Likang Xiao +6
Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants…
Aggregate and Broadcast: Scalable and Efficient Feature Interaction for Recommender Systems
Kaiyuan Li, Yongxiang Tang, Wenzheng Shu +5
Feature interaction is a core ingredient in ranking models for large-scale recommender systems, yet making it both expressive and efficiently scalable remains challenging. Exhausti…
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…
Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems
Wenzheng Shu, Yanxiang Zeng, Yongxiang Tang +6
Offline reinforcement learning (RL) has emerged as a prevalent and effective methodology for real-world recommender systems, enabling learning policies from historical data and cap…