Jaegul Choo
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×1Crypto×1NLP×1
Frequent co-authors
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