collaborators

7 papers

cs.LG2026

Measuring Explainer Stability via Attribution Separability

Eddie Conti, Álvaro Parafita, Álvaro Parafita +1

Attribution methods (AMs) assign an importance score to each feature and are widely adopted to explain black-box models. However, most methods can produce variable attribution scor…

cs.LG2026

CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals

Tomàs Garriga, Gerard Sanz, Eduard Serrahima de Cambra +1

The ability to accurately perform counterfactual inference on time series is crucial for decision-making in fields like finance, healthcare, and marketing, as it allows us to under…

cs.LG2026

Exactly Computing do-Shapley Values

R. Teal Witter, Álvaro Parafita, Tomas Garriga +4

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapl…

cs.LG2026

Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

Álvaro Parafita, Tomas Garriga, Axel Brando +1

Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional qu…

cs.LG2025

CID: Measuring Feature Importance Through Counterfactual Distributions

Eddie Conti, Álvaro Parafita, Axel Brando

Assessing the importance of individual features in Machine Learning is critical to understand the model's decision-making process. While numerous methods exist, the lack of a defin…

cs.CV2025

Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix

Unai Gurbindo, Axel Brando, Jaume Abella +1

Enhancing the robustness of object detection systems under adverse weather conditions is crucial for the advancement of autonomous driving technology. This study presents a novel a…