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
32.55/100
前 21.6%
全站排名 #13,912
发表论文5 篇
平均评分
年均产出2.5 篇/年
Xiaozhi Wang
研究方向
Mechanistic Interpretability · Language Models · Information Extraction
19
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
NeurIPS 2025Poster
二作19
Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
ICLR 2025Poster
二作17
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
ICLR 2025Rejected
二作