activity
20242026
collaborators

10 papers

cs.CL2026

Agreement in Representation Space for Open-Ended Self-Consistency

Paula Ontalvilla, Gorka Azkune, Aitor Ormazabal

Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefor…

cs.LG2026

Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning

Jon Irureta, Gorka Azkune, Jon Imaz +2

Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance and healthcare. However, most exi…

cs.CV2026

Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference

Imanol Miranda, Ander Salaberria, Eneko Agirre +1

Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that thi…

cs.CL2026

Multimodal LLMs Do Not Compose Skills Optimally Across Modalities

Paula Ontalvilla, Aitor Ormazabal, Gorka Azkune

Skill composition is the ability to combine previously learned skills to solve new tasks. As neural networks acquire increasingly complex skills during their pretraining, it is not…

cs.CL2026

Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque

Lukas Arana, Julen Etxaniz, Ander Salaberria +1

Current Multimodal Large Language Models exhibit very strong performance for several demanding tasks. While commercial MLLMs deliver acceptable performance in low-resource language…

cs.CV2025

Adding simple structure at inference improves Vision-Language Compositionality

Imanol Miranda, Ander Salaberria, Eneko Agirre +1

Dual encoder Vision-Language Models (VLM) such as CLIP are widely used for image-text retrieval tasks. However, those models struggle with compositionality, showing a bag-of-words-…