7 papers
GAPO: Robust Advantage Estimation for Real-World Code LLMs
Jianqing Zhang, Zhezheng Hao, Wei Xia +7
Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their crit…
AP2O-Coder: Adaptively Progressive Preference Optimization for Reducing Compilation and Runtime Errors in LLM-Generated Code
Jianqing Zhang, Wei Xia, Hande Dong +2
LLMs' code generation capabilities have yielded substantial improvements in the effectiveness of programming tasks. However, LLM-generated code still suffers from compilation and r…
PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
Jianqing Zhang, Yang Liu, Jie Fu +4
The rise of generative APIs has fueled interest in privacy-preserving synthetic data generation. While the Private Evolution (PE) algorithm generates Differential Privacy (DP) synt…
HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark
Jianqing Zhang, Xinghao Wu, Yanbing Zhou +7
As AI evolves, collaboration among heterogeneous models helps overcome data scarcity by enabling knowledge transfer across institutions and devices. Traditional Federated Learning…
Adaptive Guidance for Local Training in Heterogeneous Federated Learning
Jianqing Zhang, Yang Liu, Yang Hua +2
Model heterogeneity poses a significant challenge in Heterogeneous Federated Learning (HtFL). In scenarios with diverse model architectures, directly aggregating model parameters i…
PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark
Jianqing Zhang, Yang Liu, Yang Hua +5
Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL)has gain…