2025 "feature attribution" Papers
7 papers found
Boosting the visual interpretability of CLIP via adversarial fine-tuning
Shizhan Gong, Haoyu LEI, Qi Dou et al.
ICLR 2025poster
7
citations
Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI
Won Jun Kim, Hyungjin Chung, Jaemin Kim et al.
CVPR 2025posterarXiv:2411.15265
2
citations
Minimizing False-Positive Attributions in Explanations of Non-Linear Models
Anders Gjølbye, Stefan Haufe, Lars Kai Hansen
NEURIPS 2025posterarXiv:2505.11210
1
citations
Provably Accurate Shapley Value Estimation via Leverage Score Sampling
Christopher Musco, R. Teal Witter
ICLR 2025posterarXiv:2410.01917
14
citations
Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
R. Teal Witter, Yurong Liu, Christopher Musco
NEURIPS 2025posterarXiv:2506.11849
2
citations
Rethinking Shapley Value for Negative Interactions in Non-convex Games
Wonjoon Chang, Myeongjin Lee, Jaesik Choi
ICLR 2025poster
SHAP values via sparse Fourier representation
Ali Gorji, Andisheh Amrollahi, Andreas Krause
NEURIPS 2025spotlightarXiv:2410.06300
2
citations