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

Hui Zhang

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×5Crypto×2Vision×1Audio and Speech Processing×1Sound×1NLP×1

Frequent co-authors

Wenhui Zhang2×
Jie Gao1×
Jie Ma1×
Kaihui Lin1×
Kai Ye1×
Miaohui Zhang1×

Research Timeline

2026
LoopTrap: Termination Poisoning Attacks on LLM Agents

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

Grimlock: Guarding High-Agency Systems with eBPF and Attested Channels

Grimlock is an Agent Guard that enhances security for high-agency systems by enforcing identity, authorization, and scope-bound communication through eBPF and attested TLS channels, without modifying user-level orchestration code.

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

A Unified and Reproducible Experimentation Framework for Speech Understanding

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

SkyShield: Occupancy as a Safety Interface for Low-Altitude UAV Autonomy

The paper introduces SkyShield, the first front-view monocular semantic occupancy benchmark for low-altitude urban UAV flight, along with a novel metric and model to address the unique safety challenges of aerial navigation.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentMay 30, 2026

SkyShield: Occupancy as a Safety Interface for Low-Altitude UAV Autonomy

Jie Gao, Jie Ma, Kaihui Lin, Kai Ye +3 more

The paper introduces SkyShield, the first front-view monocular semantic occupancy benchmark for low-altitude urban UAV flight, along with a novel metric and model to address the unique safety challeng…

View →
eess.AScs.AIcs.SDRecentMay 29, 2026

A Unified and Reproducible Experimentation Framework for Speech Understanding

Jing Peng, Junhao Du, Chenghao Wang, Hanqi Li +20 more

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

View →
cs.CLcs.AIRecentMay 28, 2026

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

Huawei Zheng, Sen Yang, Zhaorui Yang, Yuhui Zhang +11 more

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

View →
cs.CRcs.AIRecentMay 26, 2026

Grimlock: Guarding High-Agency Systems with eBPF and Attested Channels

Qiancheng Wu, Wenhui Zhang, Gan Fang, Sheng Mao +4 more

Grimlock is an Agent Guard that enhances security for high-agency systems by enforcing identity, authorization, and scope-bound communication through eBPF and attested TLS channels, without modifying…

View →
cs.CRcs.AIRecentMay 7, 2026

LoopTrap: Termination Poisoning Attacks on LLM Agents

Huiyu Xu, Zhibo Wang, Wenhui Zhang, Ziqi Zhu +3 more

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

View →