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

Hao Wei

4 indexed papers

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

Publications per year

4
26

Top categories

NLP×2ML×2AI×2Vision×1Robotics×1Crypto×1

Frequent co-authors

Zichao Wei1×
Hongyuan Adam Lu1×
Z. L. Victor Wei1×
Qun Zhang1×
Jinrui Zeng1×
Bowen Cao1×

Research Timeline

2026
SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

SkillAttack is a red-teaming framework that dynamically tests the exploitability of latent vulnerabilities in LLM agent skills using adversarial prompting, demonstrating that even benign skills pose significant security risks.

RiskFlow: Fast and Faithful Safety-Critical Traffic Scenario Generation

RiskFlow is a novel framework that generates realistic and safety-critical multi-agent traffic scenarios by reformulating trajectory generation as a single-pass transport problem in the action space.

Looped World Models

Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.

On the Role of Directionality in Structural Generalization

The authors redesigned the symbolic backend of a SLOG test system using CCG directed types and achieved better performance than the previous SOTA.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.LGEmpiricalRecentJul 2, 2026

On the Role of Directionality in Structural Generalization

Zichao Wei

The authors redesigned the symbolic backend of a SLOG test system using CCG directed types and achieved better performance than the previous SOTA.

View →
cs.LGcs.AIcs.CLEmpirical
Recent
Jun 16, 2026

Looped World Models

Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang, Jinrui Zeng +27 more

Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.

View →
cs.ROcs.AIRecentJun 4, 2026

RiskFlow: Fast and Faithful Safety-Critical Traffic Scenario Generation

Qi Lan, Yining Tang, Yu Shen, Yi Zhou +3 more

RiskFlow is a novel framework that generates realistic and safety-critical multi-agent traffic scenarios by reformulating trajectory generation as a single-pass transport problem in the action space.

View →
cs.CRRecentApr 5, 2026

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Zenghao Duan, Yuxin Tian, Zhiyi Yin, Liang Pang +5 more

SkillAttack is a red-teaming framework that dynamically tests the exploitability of latent vulnerabilities in LLM agent skills using adversarial prompting, demonstrating that even benign skills pose s…

View →