Jian Liang

Attend to the Active: Structure-Aware Dynamic Attention in LLMs for Compositional Instruction Following

ALM-MTA: Front-Door Causal Multi-Touch Attribution Method for Creator-Ecosystem Optimization

Addressing Data Heterogeneity Through a Pre-learned Manifold for Distributed Learning Scenarios

Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

Multi-Epoch Learning with Data Augmentation for Deep Click-Through Rate Prediction