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
56.34/100
前 6%
全站排名 #3,837
发表论文5 篇
平均评分
年均产出2.5 篇/年
Mateo Espinosa Zarlenga
研究方向
explainable AI · interpretable AI · deep learning · natural language processing · concept-based explainability
30
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
NeurIPS 2025Poster
25
Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
ICLR 2025Poster
三作13
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
ICML 2025Poster
通讯9
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
ICML 2025Poster
一作