Luca Bortolussi

Full Professor@University of Trieste·意大利·OpenReview

研究方向

Explainable AI · Generative models · Neurosymbolic AI · Deep Learning · Bayesian Machine Learning · Stochastic Modelling · Formal Methods · Computational Systems Biology

7.0

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

ICLR 2025Poster

三作

4.3

Carefully Blending Adversarial Training and Purification Improves Adversarial Robustness

NeurIPS 2024Rejected

三作

4.0

CARSO: Blending Adversarial Training and Purification Improves Adversarial Robustness

ICLR 2024Rejected

三作

3.5

Relating Implicit Bias and Adversarial Attacks through Intrinsic Dimension

合作者 (8)