Guangchen Lan
YOU?
Author Swipe
View article: Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
Contextual Integrity in LLMs via Reasoning and Reinforcement Learning Open
As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central question to the field. W…
View article: Enhanced Real-Time Threat Detection in 5G Networks: A Self-Attention RNN Autoencoder Approach for Spectral Intrusion Analysis
Enhanced Real-Time Threat Detection in 5G Networks: A Self-Attention RNN Autoencoder Approach for Spectral Intrusion Analysis Open
In the rapidly evolving landscape of 5G technology, safeguarding Radio Frequency (RF) environments against sophisticated intrusions is paramount, especially in dynamic spectrum access and management. This paper presents an enhanced experim…
View article: Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization Open
Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite it…
View article: Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis Open
To improve the efficiency of reinforcement learning (RL), we propose a novel asynchronous federated reinforcement learning (FedRL) framework termed AFedPG, which constructs a global model through collaboration among $N$ agents using policy…
View article: Communication Efficient and Privacy-Preserving Federated Learning Based on Evolution Strategies
Communication Efficient and Privacy-Preserving Federated Learning Based on Evolution Strategies Open
Federated learning (FL) is an emerging paradigm for training deep neural networks (DNNs) in distributed manners. Current FL approaches all suffer from high communication overhead and information leakage. In this work, we present a federate…
View article: Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates Open
Federated reinforcement learning (FedRL) enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead remains a critical bottleneck, particularly for natural policy gra…
View article: Communication-Efficient Federated Learning for Resource-Constrained Edge Devices
Communication-Efficient Federated Learning for Resource-Constrained Edge Devices Open
Federated learning (FL) is an emerging paradigm to train a global deep neural network (DNN) model by collaborative clients that store their private data locally through the coordination of a central server. A major challenge is a high comm…
View article: Polarized double dressing control of biphotons interference and quantum tomography
Polarized double dressing control of biphotons interference and quantum tomography Open
We research the polarized dressing control of biphotons interference and quantum tomography. Different biphotons counting rates are obtained by different polarization dressings of incident beams of lights. We calculated the counting rates …
View article: Three-photon polarized entanglement and interference generated using six-wave mixing and polarized dressing atomic coherence control
Three-photon polarized entanglement and interference generated using six-wave mixing and polarized dressing atomic coherence control Open
In a spontaneous process, laser-polarized dressings produce characteristic triphoton waveforms regarding the oscillation period and coherence time. Correspondingly, circularly polarized dressings make it have longer oscillation periods com…