Fengli Xu

Beyond K-Anonymity: Protect Your Trajectory from Semantic Attack

2017

Nowadays, human trajectories are widely collected and utilized for scientific research and business purpose. However, publishing trajectory data without proper handling might cause severe privacy leakage. A large body of works are dedicated to merging …

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router

2025 · arXiv (Cornell University)

Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among multiple …