Xin Xin

How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective

OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs

Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation