M.A. (Matias) Valdenegro Toro, Dr

Assistant Professor for Machine Learning

Faculty of Science and Engineering

Telephone:

+31 50 36 36533

E-mail:

m.a.valdenegro.toro rug.nl

ORCID Research Portal

Research interests

My research interests are in building trustworthy machine learning models with real-world data for several applications, including medical AI and Robotics. These relate to Uncertainty Estimation, Computer Vision, and Explainable AI.

Publications

A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation

Abdelrahman, A. F., Valdenegro-Toro, M., Bennewitz, M. & Plöger, P. G., 8-Apr-2024, (E-pub ahead of print) In: International Journal of Robotics Research. 36 p.

Research output: Contribution to journal › Article › Academic › peer-review

Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation

Tashu, T. M., Kontos, E.-R., Sabatelli, M. & Valdenegro-Toro, M., 12-Jan-2024, (Submitted) arXiv, 12 p.

Research output: Working paper › Preprint › Academic

Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models

Groot, T. & Valdenegro-Toro, M., 5-May-2024, (Accepted/In press) Proceedings of TrustNLP Workshop @ NAACL 2024.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Transferring BCI models from calibration to control: Observing shifts in EEG features

de Jong, I. P., van den Wittenboer, L. L., Valdenegro-Toro, M. & Sburlea, A. I., 14-Mar-2024, (Submitted) arXiv, 6 p.

Research output: Working paper › Preprint › Academic

Uncertainty Quantification for cross-subject Motor Imagery classification

Manivannan, P., de Jong, I. P., Valdenegro-Toro, M. & Sburlea, A. I., 14-Mar-2024, (Submitted) arXiv, 6 p.

Research output: Working paper › Preprint › Academic

DExT: Detector Explanation Toolkit

Padmanabhan, D. C., Plöger, P. G., Arriaga, O. & Valdenegro-Toro, M., 4-Jun-2023, (Submitted) Proceedings of the 1st World Conference on eXplainable Artificial Intelligence. arXiv, 49 p.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Difficulty Estimation With Action Scores for Computer Vision Tasks

Arriaga, O., Palacio, S. & Valdenegro-Toro, M., 2023, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops: LatinX in CV Workshop. IEEE, p. 245-253 9 p.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Sanity Checks for Saliency Methods Explaining Object Detectors

Padmanabhan, D. C., Plöger, P. G., Arriaga, O. & Valdenegro-Toro, M., 4-Jun-2023, (Submitted) Proceedings of the 1st World Conference on eXplainable Artificial Intelligence. arXiv, 19 p.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Sanity Checks for Saliency Methods Explaining Object Detectors

Padmanabhan, D. C., Plöger, P. G., Arriaga, O. & Valdenegro-Toro, M., 29-Oct-2023, Explainable Artificial Intelligence: First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part I. Longo, L. (ed.). Springer, p. 438-455 18 p. (Communications in Computer and Information Science; vol. 1901 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Sub-Ensembles for Fast Uncertainty Estimation in Neural Networks

Valdenegro-Toro, M., 1-Oct-2023, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. IEEE, p. 4119-4127 9 p.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

All (19) publications

Press/media

Participation in Podcast "Hacia Afuera"

Valdenegro Toro, M.

06/01/2023

Press/Media: Public Engagement Activities › Professional

All (1) press/media

View full research profile