11 papers
Interior interpretability with attention rollout: contraction and propagation profiles in Transformers
Umberto Biccari, Qian Huang, Enrique Zuazua
Feature-attribution methods assign scores relating input variables to a model's output, but do not by themselves characterize how explicitly defined interaction operators compose a…
Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data
Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris +3
Object detection is a fundamental capability for AI-driven perception in safety-critical drone and edge-vision systems, including disaster response, operational security environmen…
Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers
Daniel M. Jimenez-Gutierrez, Dario Pighin, Enrique Zuazua +4
Federated Learning (FL) enables collaborative model training among multiple parties without centralizing raw data. There are two main paradigms in FL: Horizontal FL (HFL), where al…
Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris +3
The recent success of large language models (LLMs) has been largely driven by vast public datasets. However, the next frontier for LLM development lies beyond public data. Much of…
Geometric Asymptotics of Score Mixing and Guidance in Diffusion Models
Kang Liu, Enrique Zuazua
Diffusion models are routinely guided in practice by combining multiple score fields, yet the mathematical structure of score mixing is still poorly understood. We study the small-…
Fair feature attribution for multi-output prediction: a Shapley-based perspective
Umberto Biccari, Alain Ibáñez de Opakua, José MarÃa Mato +3
In this article, we provide an axiomatic characterization of feature attribution for multi-output predictors within the Shapley framework. While SHAP explanations are routinely com…