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

Yunseok Lee

2 indexed papers

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

Publications per year

2
26

Top categories

Multiagent×1Vision×1Crypto×1AI×1ML×1

Frequent co-authors

Seoyoung Choi1×
Minseok Ko1×
Hyunseok Lee1×
Kunwoong Kim1×
Woomin Song1×
Chanseok Jeon1×

Research Timeline

2026
SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

The paper introduces SlotGCG, an improved jailbreak attack method that systematically searches for the most vulnerable token insertion positions (slots) within a prompt, significantly boosting attack success rates compared to fixed-position methods.

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

This paper introduces a taxonomy of GUI agent failures and finds that full-image memory has divergent effects on failure distribution. It proposes Action-Grounded Visual Memory (AGMem) as an effective alternative.

Highlighted terms show continued research focus across papers

Papers

cs.MAcs.CVEmpiricalRecentJun 12, 2026

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

Seoyoung Choi, Minseok Ko, Hyunseok Lee, Kunwoong Kim +3 more

This paper introduces a taxonomy of GUI agent failures and finds that full-image memory has divergent effects on failure distribution. It proposes Action-Grounded Visual Memory (AGMem) as an effective…

View →
cs.CRcs.AIcs.LGRecent
Jun 4, 2026

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim, Yunseok Lee +1 more

The paper introduces SlotGCG, an improved jailbreak attack method that systematically searches for the most vulnerable token insertion positions (slots) within a prompt, significantly boosting attack…

View →