Selected work

Representative Papers

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

Nov 12, 2025

High-performing open-source multimodal large language models (MLLMs) remain scarce for low-resource languages such as Basque. Method: This work proposes a lightweight, data-driven paradigm: autonomously constructing a high-quality Basque image–text dataset and performing end-to-end multimodal hybrid training using Llama-3.1-Instruct and the Basque language model Latxa as backbones—without Basque-specific instruction tuning. Contribution/Results: We find that only ~20% of Basque multimodal data suffices to achieve substantial performance gains, challenging the prevailing assumption that extensive language-specific supervision is required. The resulting model establishes new open-source state-of-the-art performance on Basque multimodal understanding tasks. All components—including the curated dataset, training code, and model checkpoints—are fully open-sourced. This work provides a reproducible, transferable methodology and empirical foundation for multimodal research in low-resource languages.

0 citationsRead paper

REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models

Jun 09, 2025

Traditional multi-objective optimization algorithms suffer from complex manual modeling, poor adaptability, and difficulty handling nonlinear problem structures. Method: This paper proposes the first large language model (LLM)-driven reflective heuristic evolutionary framework, integrating NSGA-II with LLMs to automatically generate evolvable domain-specific heuristic rules; it further introduces a dynamic-clustering-based search-space reflection mechanism to jointly enhance solution-set convergence and diversity. Contribution/Results: The framework achieves state-of-the-art (SOTA) performance on three classical flexible job-shop scheduling problem (FJSSP) benchmarks—Dauzere, Barnes, and Brandimarte—significantly reducing human modeling effort while improving algorithmic adaptability and decision interpretability.

0 citationsRead paper

Recent publications

Latest Papers

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

Nov 12, 2025

High-performing open-source multimodal large language models (MLLMs) remain scarce for low-resource languages such as Basque. Method: This work proposes a lightweight, data-driven paradigm: autonomously constructing a high-quality Basque image–text dataset and performing end-to-end multimodal hybrid training using Llama-3.1-Instruct and the Basque language model Latxa as backbones—without Basque-specific instruction tuning. Contribution/Results: We find that only ~20% of Basque multimodal data suffices to achieve substantial performance gains, challenging the prevailing assumption that extensive language-specific supervision is required. The resulting model establishes new open-source state-of-the-art performance on Basque multimodal understanding tasks. All components—including the curated dataset, training code, and model checkpoints—are fully open-sourced. This work provides a reproducible, transferable methodology and empirical foundation for multimodal research in low-resource languages.

0 citationsRead paper

REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models

Jun 09, 2025

Traditional multi-objective optimization algorithms suffer from complex manual modeling, poor adaptability, and difficulty handling nonlinear problem structures. Method: This paper proposes the first large language model (LLM)-driven reflective heuristic evolutionary framework, integrating NSGA-II with LLMs to automatically generate evolvable domain-specific heuristic rules; it further introduces a dynamic-clustering-based search-space reflection mechanism to jointly enhance solution-set convergence and diversity. Contribution/Results: The framework achieves state-of-the-art (SOTA) performance on three classical flexible job-shop scheduling problem (FJSSP) benchmarks—Dauzere, Barnes, and Brandimarte—significantly reducing human modeling effort while improving algorithmic adaptability and decision interpretability.

0 citationsRead paper