activity
19992026
most citedOptimising and comparing source extraction tools using objective segmentation quality criteria

34 citations · 94 across the 42 of their papers we have counts for

collaborators
Showing 2026Show all

13 papers · 1 filter

cs.SD2026

Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition

Nico García-Peguinho, David Kelly, Fabrizio Smeraldi +1

Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to the retained signal. Yet they…

stat.ML2026

Matrix Aggregation Operators

Inmaculada Gutiérrez, Asier Urio-Larrea, J. Tinguaro Rodríguez +3

Aggregation theory has traditionally focused on operators defined over vectors. However, many applications-including Multi-Criteria Decision Making, Group Decision Making, Fuzzy Ru…

cs.CV2026

GERIS: A Game-Theoretic Framework for Filtering Instance-Dependent Label Noise in License Plate Data Augmentation

Seyedeh Sara Jalili Shani, Rouhollah Ahmadian, Amin Rahmani +2

In this paper, we propose GERIS, a game-theoretic framework for instance selection in the data augmentation phase of license plate recognition systems. During augmentation, synthet…

hep-ph2026

Precise QCD Predictions for the Scotogenic Model at Colliders

Mohammed Boukidi, Camila Ramos, Richard Ruiz

Motivated by the anticipated data rates of the high-luminosity phase of the Large Hadron Collider, we report the first predictions up to next-to-leading order in quantum chromodyna…

cs.CL2026

Domain-Adaptive Pretraining Enhances Water Treatment Semantic Representation for Large-Scale Structured Literature Mining

Mudi Zhai, Ruihong Qiu, Qingyun Zeng +3

Water treatment research is expanding rapidly, but much of the knowledge acquired from this research remains scattered across unstructured literature. The field still lacks a dedic…

cs.LG2026

Muon Can Outperform Dedicated Continual Learning Methods

Sebastian George Sincari, Bogdan Alexandru Gheorghe, Antonio Barbalau

Continual learning with Low-Rank Adapters (LoRA) typically mitigates forgetting by penalizing the overlap between a new update and the accumulated past weights, which discourages c…