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
67.63/100
前 3%
全站排名 #1,959
发表论文8 篇
平均评分
年均产出2.7 篇/年
Jing Gao
研究方向
Truth discovery · Knowledge graph · Multi-source data analysis · Transfer learning · Text mining · Data stream mining · Anomaly detection · Data and model efficiency · Data poisoning attack · Fairness · Interpretation · Federated learning · Large language model · Knowledge editing
9
Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
ICML 2025Poster
通讯21
SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning
COLM 2025Poster
通讯24
Towards Federated RLHF with Aggregated Client Preference for LLMs
ICLR 2025Poster
通讯32
Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
ICLR 2025Poster
通讯11
On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness
ICML 2025Poster
三作