影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
55.94/100
前 6.1%
全站排名 #3,927
发表论文10 篇
平均评分
年均产出3.3 篇/年
Minseon Kim
研究方向
AI Safety · Adversarial Robustness · Representation Learning
21
Gistify: Codebase-Level Understanding via Runtime Execution
ICLR 2026Poster
二作24
Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
ICLR 2026Poster
二作13
SafeMoE: Leveraging Unsafe Data to Train Safer, More Informative LLMs
ICLR 2026Desk Rejected
三作-1
BugPilot: Complex Bug Generation for Efficient Training of SWE Agents
ICLR 2026Desk Rejected
24
BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing
NeurIPS 2025Poster
三作25
Learning to Solve Complex Problems via Dataset Decomposition
NeurIPS 2025Poster
15
Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
COLM 2025Poster
一作10
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
COLM 2025Poster
三作34
Automatic Jailbreaking of Text-to-Image Generative AI Systems for Copyright Infringement
ICLR 2025Rejected
一作