Wanchun Dou

DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning

A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments

Policy Filtration for RLHF to Mitigate Noise in Reward Models

Policy Filtration in RLHF to Fine-Tune LLM for Code Generation

ATTENDING: Federated Learning with Personalized Attentive Pruning for Heterogeneous Clients

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices