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
58.97/100
前 5%
全站排名 #3,247
发表论文14 篇
平均评分
年均产出4.7 篇/年
Jiancheng Liu
研究方向
Large Language Models · Trustworthy Machine Learning · Differentiable Physics
22
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
NeurIPS 2025Poster
二作20
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
NeurIPS 2025Rejected
63
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
ICLR 2025Rejected
二作6
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
ICLR 2025Withdrawn