Danny Xie-Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Danny Xie-Li has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- S. Calderon Ramirez
Instituto Tecnológico de Costa Rica
3 shared publications - Fabian Fallas-Moya
Universidad de Costa Rica
2 shared publications - Manfred Gonzalez Hernandez
Ghent University, Ghent, Belgium
2 shared publications - Nelson Pérez-Rojas
Doctorado en Ciencias Naturales para el Desarrollo (DOCINADE), Instituto Tecnológico de Costa Rica, Universidad Nacional, Universidad Estatal a Distancia, San José, Costa Rica
2 shared publications - Sebastian Rojas Gonzalez
Ghent University, Ghent, Belgium
2 shared publications - Angel Garcia-Pedrero
Universidad Politécnica de Madrid
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Elsevier in Data in Brief
- Vol. 69
A step toward inclusion: A transparent dataset for automatic text simplification for screen reader users
- 1 September 2026
- Published by Elsevier in Data in Brief
- Vol. 69
Open AccessA step toward inclusion: A transparent dataset for automatic text simplification for screen reader users
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1457-1464
Peeling Back the Pixels: Stabilizing Latent Diffusion for Data-Efficient Generation of Pineapple Fields
While Latent Diffusion Models (LDMs) excel at synthetic data generation, they suffer from severe training instability on the small, homogeneous UAV datasets typical of precision agriculture. In this work, we investigate these architectural bottlenecks by training a Denoising Diffusion Probabilistic Model (DDPM) from scratch on constrained pineapple plantation imagery. Our systematic comparison reveals that continuous latent spaces (β-VAE) preserve complex crop structures, whereas discrete architectures (VQ-VAE) fail under scarce data conditions. Additionally, we demonstrate that replacing destabilizing global attention mechanisms with a purely convolutional U-Net backbone ensures smooth convergence in repetitive visual domains. Ultimately, combining this robust architecture with DDIM sampling yields a stable, highly efficient framework for low-data agricultural image synthesis. Code and models will be available at https://github.com/imagine-laboratory/Latent-Diffusion.
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1457-1464
Open AccessPeeling Back the Pixels: Stabilizing Latent Diffusion for Data-Efficient Generation of Pineapple Fields
While Latent Diffusion Models (LDMs) excel at synthetic data generation, they suffer from severe training instability on the small, homogeneous UAV datasets typical of precision agriculture. In this work, we investigate these architectural bottlenecks by training a Denoising Diffusion Probabilistic Model (DDPM) from scratch on constrained pineapple plantation imagery. Our systematic comparison reveals that continuous latent spaces (β-VAE) preserve complex crop structures, whereas discrete architectures (VQ-VAE) fail under scarce data conditions. Additionally, we demonstrate that replacing destabilizing global attention mechanisms with a purely convolutional U-Net backbone ensures smooth convergence in repetitive visual domains. Ultimately, combining this robust architecture with DDIM sampling yields a stable, highly efficient framework for low-data agricultural image synthesis. Code and models will be available at https://github.com/imagine-laboratory/Latent-Diffusion.
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1465-1473
Evolutionary Optimization of Instruction-Tuned Large Language Model Inference Parameters for Spanish Text Simplification
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1465-1473
Open AccessEvolutionary Optimization of Instruction-Tuned Large Language Model Inference Parameters for Spanish Text Simplification
- Open Access
- 9 September 2024
- Published by Instituto Tecnologico de Costa Rica in Revista Tecnología en Marcha
- Vol. 37, ág 38-43
Proposal of self and semi-supervised learning for imbalanced classification of coronary heart disease tabular data
Triple Mixup is an augmentation policy in the hidden latent space we introduced in the Contrastive Mixup Self-Semi Supervised learning framework, to address the imbalanced data problem, for Cardiovascular Heart Diseases tabular dataset. Medical tabular datasets are known to present challenges as high imbalanced class, limited annotated quality samples due to the domain nature. Recent literature in Self and Semi supervised learning, has shown tremendous progress in learning useful representations, and leveraging unlabeled dataset and labeled dataset to train a learning model. Most existing methods are not feasible for tabular data due to the data augmentation scheme. In addition, the high imbalanced problem can show lower performance on machine learning algorithms. For this work, we propose the triple data augmentation method in hidden space to attack the unbalanced challenge in self-supervised and semi-supervised learning, from the possible applications of Contrastive Mixup, thus we will study the influence of it.
- 9 September 2024
- Published by Instituto Tecnologico de Costa Rica in Revista Tecnología en Marcha
- Vol. 37, ág 38-43
Open AccessProposal of self and semi-supervised learning for imbalanced classification of coronary heart disease tabular data
Triple Mixup is an augmentation policy in the hidden latent space we introduced in the Contrastive Mixup Self-Semi Supervised learning framework, to address the imbalanced data problem, for Cardiovascular Heart Diseases tabular dataset. Medical tabular datasets are known to present challenges as high imbalanced class, limited annotated quality samples due to the domain nature. Recent literature in Self and Semi supervised learning, has shown tremendous progress in learning useful representations, and leveraging unlabeled dataset and labeled dataset to train a learning model. Most existing methods are not feasible for tabular data due to the data augmentation scheme. In addition, the high imbalanced problem can show lower performance on machine learning algorithms. For this work, we propose the triple data augmentation method in hidden space to attack the unbalanced challenge in self-supervised and semi-supervised learning, from the possible applications of Contrastive Mixup, thus we will study the influence of it.