Get started
Author

Minghui Xu

AgentDID: Trustless Identity Authentication for AI Agents
2026 · Minghui Xu, Xiaoyu Liu, et al. · IEEE International Conference on Distributed Computing Systems (ICDCS) · 1
Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning
2026 · Xu, Minghui, Wang, Zi · arXiv (Cornell University)
PDF
CIDER: Continual Interactive Distillation for Embodied Reinforcement Learning
2026 · Li, Houlin, Xu, Minghui, et al. · arXiv (Cornell University)
PDF
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents
2026 · Shan, Zhengyang, Qian, Xu, et al. · arXiv (Cornell University)
PDF
Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks
2026 · JinCheng, Ying, Xu, Minghui, et al. · arXiv (Cornell University)
PDF
"What Happens Locally, Leaks Globally": Detecting Privacy Leakage Risks in MCP Servers
2026 · Yan, Biwei, Xu, Minghui, et al. · arXiv (Cornell University)
PDF
OrbitBFT: Enabling Scalable and Robust BFT Consensus in LEO Constellations
2026 · Tianyi Sun, Shuo Liu, et al. · IEEE International Conference on Distributed Computing Systems (ICDCS)
Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs
2026 · Luo, Qi, Xu, Minghui, et al. · arXiv (Cornell University)
PDF
Almost-Free Queue Jumping for Prior Inputs in Private Neural Inference
2026 · Zhang, Qiao, Xu, Minghui, et al. · arXiv (Cornell University)
PDF
Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
2026 · Shan, Zhengyang, Xin, Jiayun, et al. · arXiv (Cornell University)
PDF
Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool Descriptions
2026 · Li, Zhihao, Ma, Boyang, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type