Weijia Lu

AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement Learning

ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning

Improving Policy Optimization via Enhanced Exploration

Learning to Think in Blocks: A Prior-Guided Reinforcement Learning Framework for RAG

BPO: Revisiting Preference Modeling in Direct Preference Optimization

LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation

FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates

FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates

Exchange of Perspective Prompting Enhances Reasoning in Large Language Models