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

Jaegul Choo

2 indexed papers

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

Publications per year

2
26

Top categories

AI×1Crypto×1NLP×1

Frequent co-authors

Jinho Choi1×
Hyesu Lim1×
Steffen Schneider1×
Minseok Choi1×
Seungbin Yang1×
Dongjin Kim1×

Research Timeline

2026
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Membrane introduces a self-evolving guardrail using Contrastive Safety Memory (CSM) that generalizes across topical jailbreak variants, achieving superior safety performance while minimizing benign refusal rates.

Beyond SAEs: Consistent Concept Discovery with Sparse Coding

The paper proposes Consistent Sparse Dictionary Learning (ConSDL) to improve the reliability and reproducibility of sparse autoencoders.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentOct 16, 2026

Beyond SAEs: Consistent Concept Discovery with Sparse Coding

Jinho Choi, Hyesu Lim, Jaegul Choo, Steffen Schneider

The paper proposes Consistent Sparse Dictionary Learning (ConSDL) to improve the reliability and reproducibility of sparse autoencoders.

View →
cs.CRcs.CLRecentJun 4, 2026

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Minseok Choi, Seungbin Yang, Dongjin Kim, Subin Kim +4 more

Membrane introduces a self-evolving guardrail using Contrastive Safety Memory (CSM) that generalizes across topical jailbreak variants, achieving superior safety performance while minimizing benign re…

View →