305 citations · 703 across the 28 of their papers we have counts for
30 papers
SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation
Zeno Testa, Antonino Furnari, Lorenzo Baraldi +1
Sign Language Translation (SLT) is typically evaluated with surface-form metrics such as BLEU and ROUGE, which reward lexical overlap but do not directly measure whether a translat…
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
David Méndez, Roberto Confalonieri, Natalia Díaz Rodríguez
Vision-Language Models (VLMs) excel at tasks like zero-shot classification and cross-modal retrieval by mapping images and text to a shared space, but this requires expensive end-t…
The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic
Dominika Agnieszka Długosz, Arlindo Oliveira, Natalia Díaz-Rodríguez
The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-generated variants of GSM8K…
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
Carmen Quiles-Ramírez, Leticia L. Rodríguez, Nicolás Martorell +1
In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains o…
CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs
David Méndez, Gianpaolo Bontempo, Elisa Ficarra +2
Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts a…
Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation
Natalia Díaz-Rodríguez, Javier Del Ser, Mark Coeckelbergh +3
Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it…
Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using Myerson values
Giorgio Angelotti, Natalia Díaz-Rodríguez
A quantitative assessment of the global importance of an agent in a team is as valuable as gold for strategists, decision-makers, and sports coaches. Yet, retrieving this informati…
Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification
Adrien Bennetot, Gianni Franchi, Javier Del Ser +2
Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep l…
Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generation
Tomas Cabezon Pedroso, Javier Del Ser, Natalia Diaz-Rodrıguez
Rendering programs have changed the design process completely as they permit to see how the products will look before they are fabricated. However, the rendering process is complic…
Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization
Javier Del Ser, Alejandro Barredo-Arrieta, Natalia Díaz-Rodríguez +2
There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on…
Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values
Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-Rodríguez
While Explainable Artificial Intelligence (XAI) is increasingly expanding more areas of application, little has been applied to make deep Reinforcement Learning (RL) more comprehen…
Questioning causality on sex, gender and COVID-19, and identifying bias in large-scale data-driven analyses: the Bias Priority Recommendations and Bias Catalog for Pandemics
Natalia Díaz-Rodríguez, Rūta Binkytė-Sadauskienė, Wafae Bakkali +4
The COVID-19 pandemic has spurred a large amount of observational studies reporting linkages between the risk of developing severe COVID-19 or dying from it, and sex and gender. By…
Explaining Credit Risk Scoring through Feature Contribution Alignment with Expert Risk Analysts
Ayoub El Qadi, Natalia Diaz-Rodriguez, Maria Trocan +1
Credit assessments activities are essential for financial institutions and allow the global economy to grow. Building robust, solid and accurate models that estimate the probabilit…
Physics-informed GANs for Coastal Flood Visualization
Björn Lütjens, Brandon Leshchinskiy, Christian Requena-Mesa +8
As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, but during h…
Explainability in Deep Reinforcement Learning
Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-Rodríguez
A large set of the explainable Artificial Intelligence (XAI) literature is emerging on feature relevance techniques to explain a deep neural network (DNN) output or explaining mode…
Should artificial agents ask for help in human-robot collaborative problem-solving?
Adrien Bennetot, Vicky Charisi, Natalia Díaz-Rodríguez
Transferring as fast as possible the functioning of our brain to artificial intelligence is an ambitious goal that would help advance the state of the art in AI and robotics. It is…
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Stephane Doncieux, Nicolas Bredeche, Léni Le Goff +9
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors. Learning algorithm…
Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models
Pranav Agarwal, Alejandro Betancourt, Vana Panagiotou +1
Image captioning models have been able to generate grammatically correct and human understandable sentences. However most of the captions convey limited information as the model us…
Towards Explainable Neural-Symbolic Visual Reasoning
Adrien Bennetot, Jean-Luc Laurent, Raja Chatila +1
Many high-performance models suffer from a lack of interpretability. There has been an increasing influx of work on explainable artificial intelligence (XAI) in order to disentangl…
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
Alejandro Barredo Arrieta, Natalia Díaz-Rodríguez, Javier Del Ser +9
In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this t…
DisCoRL: Continual Reinforcement Learning via Policy Distillation
René Traoré, Hugo Caselles-Dupré, Timothée Lesort +4
In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of…
Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges
Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian +3
Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and object…
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
René Traoré, Hugo Caselles-Dupré, Timothée Lesort +3
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encoun…
Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
Antonin Raffin, Ashley Hill, René Traoré +3
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learni…