activity
20242026
collaborators

8 papers

cs.IR2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Lingyuan Kong, Jiaqi Cui, Fanjiao Zeng +6

Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cros…

cs.IR2026

Once Generated, Ranked: End-to-End Generative Slate Recommendation with Unified Semantic-Collaborative IDs

Yang Hu, Jiayi Guo, Jingui Ma +6

Slate recommendation treats a slate rather than an individual item as the recommendation unit, requiring joint optimization of item interactions and slate utility. Existing approac…

cs.IR2025

xMTF: A Formula-Free Model for Reinforcement-Learning-Based Multi-Task Fusion in Recommender Systems

Yang Cao, Changhao Zhang, Xiaoshuang Chen +2

Recommender systems need to optimize various types of user feedback, e.g., clicks, likes, and shares. A typical recommender system handling multiple types of feedback has two compo…

cs.IR2025

Creator-Side Recommender System: Challenges, Designs, and Applications

Xiaoshuang Chen, Yibo Wang, Yao Wang +4

Users and creators are two crucial components of recommender systems. Typical recommender systems focus on the user side, providing the most suitable items based on each user's req…

cs.LG2024

RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems

Shuo Su, Xiaoshuang Chen, Yao Wang +5

Modern recommender systems are built upon computation-intensive infrastructure, and it is challenging to perform real-time computation for each request, especially in peak periods,…

cs.LG2024

Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems

Xiaoshuang Chen, Gengrui Zhang, Yao Wang +4

Modern large-scale recommender systems are built upon computation-intensive infrastructure and usually suffer from a huge difference in traffic between peak and off-peak periods. I…