影响力指数

38.95/100

前 15.2%

全站排名 #9,767

发表论文3 篇

平均评分6.6

年均产出1.5 篇/年

Jingnan Zheng

PhD student@National University of Singapore·新加坡·OpenReview

研究方向

trustworthy ai · recommendation system

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

NeurIPS 2025Poster

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

NeurIPS 2025Poster

ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation

NeurIPS 2024Poster

合作者 (14)

博士导师3 篇