3 papers
cs.CL2026
Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models
Junxiang Qiu, Shuo Wang, Zhengsu Chen +4
Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due…
cs.IR2025
Personalized Tree-Based Progressive Regression Model for Watch-Time Prediction in Short Video Recommendation
Xiaokai Chen, Xiao Lin, Changcheng Li +1
In online video platforms, accurate watch time prediction has become a fundamental and challenging problem in video recommendation. Previous research has revealed that the accuracy…
cs.LG2024
LDACP: Long-Delayed Ad Conversions Prediction Model for Bidding Strategy
Peng Cui, Yiming Yang, Fusheng Jin +8
In online advertising, once an ad campaign is deployed, the automated bidding system dynamically adjusts the bidding strategy to optimize Cost Per Action (CPA) based on the number…