Xiao Zhang

Achieving Better Utility beyond LDP-FL by Independent Two-phase Protection

SAGE: Adaptive Self-Training Towards Endogenous Memory in Large Language Models

DP-C4: Eliminating Solution Bias in Differentially Private Optimization via Coupled Clipping with Adaptive Thresholds

Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood

Score-based free-form architectures for high-dimensional Fokker-Planck equations

ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble

NF-MKV Net: A Constraint-Preserving Neural Network Approach to Solving Mean-Field Games Equilibrium