2 papers
cs.CL2026
Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models
Zihao Guo, Hongtao Lv, Chaoli Zhang +4
Although Large Language Models (LLMs) demonstrate remarkable capabilities in reasoning and decision-making, high-fidelity probabilistic sampling remains a persistent challenge. Whe…
cs.LG2025
FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures
Jiacheng Wang, Hongtao Lv, Lei Liu
Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model…