Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Mengxuan Lu

Mengxuan Lu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Audio and Speech Processing×1NLP×1Sound×1Robotics×1Crypto×1

Frequent co-authors

Xinwei Cao1×
Torbjørn Svendsen1×
Giampiero Salvi1×
Zhen Huang1×
Zhihuang Liu1×
Mengxuan Luo1×

Research Timeline

2026
Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration via Single Robot Compromise

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe actions across the entire system.

Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection

The paper proposes a Lagrangian sub-flow (LSF) framework and geometric diagnostic signals to improve out-of-distribution detection using Continuous Normalizing Flows, overcoming the likelihood paradox in high-dimensional data.

Highlighted terms show continued research focus across papers

Papers

eess.AScs.CLcs.SDRecentMay 30, 2026

Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection

Xinwei Cao, Mengxuan Lu, Torbjørn Svendsen, Giampiero Salvi

The paper proposes a Lagrangian sub-flow (LSF) framework and geometric diagnostic signals to improve out-of-distribution detection using Continuous Normalizing Flows, overcoming the likelihood paradox…

View →
cs.ROcs.CRRecentMay 15, 2026

Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration via Single Robot Compromise

Zhen Huang, Zhihuang Liu, Mengxuan Luo, Weishang Wu +1 more

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

View →