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

Hang Zhang

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×2Crypto×2Vision×1ML×1

Frequent co-authors

Shihang Zhang1×
Mingjin Kuai1×
Ye Wei1×
Zhen Zhang1×
Wei Ji1×
Yuting Xu1×

Research Timeline

2026
TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

The paper introduces TRUSTDESC, a novel framework that prevents tool poisoning attacks in LLM applications by automatically generating highly accurate and trusted tool descriptions directly from the tool's source code and behavior.

Lossless Anti-Distillation Sampling

The paper introduces Lossless Anti-Distillation Sampling (LADS), a novel sampling scheme that makes harvested data correlated for malicious distillers while ensuring benign users receive statistically undistorted responses.

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

The paper introduces VeriTrip, a new verifiable benchmark that evaluates travel planning agents' ability to perform evidence-grounded reasoning over complex, unstructured, and multimodal web data, revealing a critical retrieval-reasoning trade-off.

GIRL-DETR: Gradient-Isolated Reinforcement Learning for Video Moment Retrieval

GIRL-DETR introduces Gradient-Isolated Reinforcement Learning to enhance temporal localization in lightweight Video Moment Retrieval models, achieving high accuracy by decoupling feature representation from metric optimization.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentMay 30, 2026

GIRL-DETR: Gradient-Isolated Reinforcement Learning for Video Moment Retrieval

Shihang Zhang, Mingjin Kuai, Ye Wei, Zhen Zhang +1 more

GIRL-DETR introduces Gradient-Isolated Reinforcement Learning to enhance temporal localization in lightweight Video Moment Retrieval models, achieving high accuracy by decoupling feature representatio…

View →
cs.AIRecentMay 27, 2026

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

Yuting Xu, Jiayi Tian, Jian Liang, Xin Xiong +3 more

The paper introduces VeriTrip, a new verifiable benchmark that evaluates travel planning agents' ability to perform evidence-grounded reasoning over complex, unstructured, and multimodal web data, rev…

View →
cs.LGcs.CRRecentMay 12, 2026

Lossless Anti-Distillation Sampling

Zibo Diao, Jingchu Gai, Xinyue Ai, Zhang Zhang +2 more

The paper introduces Lossless Anti-Distillation Sampling (LADS), a novel sampling scheme that makes harvested data correlated for malicious distillers while ensuring benign users receive statistically…

View →
cs.CRRecentApr 8, 2026

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Hengkai Ye, Zhechang Zhang, Jinyuan Jia, Hong Hu

The paper introduces TRUSTDESC, a novel framework that prevents tool poisoning attacks in LLM applications by automatically generating highly accurate and trusted tool descriptions directly from the t…

View →