paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
LC

Li Chen

ACL 2026×2ICML 2026安全对齐与偏好强化学习与后训练多模态数据与预训练
新星分资深
21
一作贡献0
核心/参与5
方向广度13
合作网络6
0 一作 · 3 篇 · ACL 2026 / ICML 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
作者位次 #6/9ACL 2026Poster· Natural Language Processing

Jailbreak-Zero: A Path to P areto Optimal Red Teaming for Large Language Models

Kai Hu · Abhinav Aggarwal · Mehran Khodabandeh · David Zhang · Eric Hsin · Li Chen · Ankit Jain · Matt Fredrikson · Akash Bharadwaj

摘要

This paper presents a novel Automated Red Teaming (ART) framework that shifts from example-based to policy-based evaluation, addressing critical limitations in scalability and validity. We define harmful content through abstract safety policies rather than specific static examples. We also introd...

安全对齐与偏好强化学习与后训练OpenReview 项目页
作者位次 #9/9ACL 2026Findings· Findings of ACL

Red-Teaming NSFW Image Classifiers as Text-to-Image Safeguards

Tinghao Xie · Yueqi Xie · Alireza Zareian · Shuming Hu · Felix Juefei-Xu · Xiaowen Lin · Ankit Jain · Prateek Mittal · Li Chen

摘要

Not Safe for Work (NSFW) image classifiers play a critical role in safeguarding text-to-image (T2I) systems. However, a concerning phenomenon has emerged in T2I systems – changes in text prompts that manipulate benign image elements can result in failed detection by NSFW classifiers – dubbed “ co...

安全多模态数据与预训练OpenReview 项目页

常见合作者