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

Zhe Hu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2NLP×1Vision×1ML×1physics.comp-ph×1Crypto×1

Frequent co-authors

Yi Zhao1×
Siqi Wang1×
Yushi Li1×
Jing Li1×
Yuxin Wang1×
Yuanzhe Hu1×

Research Timeline

2026
Re-Triggering Safeguards within LLMs for Jailbreak Detection

The paper introduces an embedding disruption method to re-activate and strengthen built-in safeguards within LLMs, effectively detecting and defending against sophisticated jailbreak attacks.

Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime-aware diagnostic approach.

A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation

The paper introduces VIABLE, the first benchmark for evaluating Vision-Language Models (VLMs) as judges for Visually Impaired Assistance (VIA), finding that current models are largely unreliable and proposing VIA-Judge-Agent to improve evaluation.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.CVRecentMay 29, 2026

A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation

Yi Zhao, Siqi Wang, Zhe Hu, Yushi Li +1 more

The paper introduces VIABLE, the first benchmark for evaluating Vision-Language Models (VLMs) as judges for Visually Impaired Assistance (VIA), finding that current models are largely unreliable and p…

View →
cs.LGcs.AIphysics.comp-phRecentMay 27, 2026

Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization

Yuxin Wang, Yuanzhe Hu, Xiaokun Zhong, Xiaopeng Wang +6 more

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime…

View →
cs.CRcs.AIRecentMay 11, 2026

Re-Triggering Safeguards within LLMs for Jailbreak Detection

Zheng Lin, Zhenxing Niu, Haoxuan Ji, Yuzhe Huang +1 more

The paper introduces an embedding disruption method to re-activate and strengthen built-in safeguards within LLMs, effectively detecting and defending against sophisticated jailbreak attacks.

View →