Pablo M. Olmos

Multi-View Oriented GPLVM: Expressiveness and Efficiency. Zi Yang, Ying Li, Zhidi Lin, Michael Minyi Zhang, Pablo M. Olmos

In an article that reviews current challenges and trends in AI, El País newspaper interviewed me to discuss on Large World Models (in Spanish).

I had the pleasure of being one of the organizers of MLSS 2025 in Arequipa, Perú. An outstanding group of speakers and students came together for 13 days of engaging seminars and discussions. It was truly a wonderful experience.

Scalable Random Feature Latent Variable Models . Ying Li, Zhidi Lin, Yuhao Liu, Michael Minyi Zhang, Pablo M. Olmos, Petar M. Djurić

Our Marie Skłodowska-Curie 2024 Doctoral Network Machine Learning Computational Advancements for peRsonalized mEdicine (MLCARE), has been granted, and the grant agreement has been signed by all parties. The project will officially start in January 2026, and I am honored to serve as the project coordinator.

MLCARE aims to push the frontiers of AI for personalized medicine and life sciences, bringing together a fantastic consortium: UC3M, MPG, ULiege, LMU, U. Paris Cité, UTartu, UCPH, ETH Zürich, FPS, AstraZeneca, Pharmatics, HMNC — with support from Oxford, Inst. Pasteur, Siemens, Novo Nordisk, eB2, Pixelgen, University of Maastricht, and Instituto de Investigación Sanitaria Gregorio Marañón.

Soon, we will be looking for PhD students to join the adventure!

Improved Variational Inference in Discrete VAEs using Error Correcting Codes . María Martínez-García, Grace Villacrés, David Mitchell, Pablo M. Olmos

El País recently interviewed me about my research on generative AI and my FBBVA Leonardo Grant. You can read the full interview here (in Spanish).

I’m excited to announce that my project, “THAI: Towards Humble and Discoverable AI,” has been awarded a grant by the FBBVA Leonardo Program. This year, only 57 out of 1,423 projects were selected (a 4% acceptance rate), making this recognition even more special. We are currently looking for a post-doctoral researcher to join our team and contribute to the project.

Diffusion X-ray image denoising. Daniel Sanderson, Pablo M. Olmos, Carlos Fernández Del Cerro, Manuel Desco, Mónica Abella

Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks. Mikkel Jordahn, Pablo M. Olmos

Training Implicit Generative Models via an Invariant Statistical Loss. Jose Manuel de Frutos, Pablo M. Olmos, Manuel Alberto Vázquez, Joaquín Míguez

Efficient local linearity regularization to overcome catastrophic overfitting. Elias Abad Rocamora, Fanghui Liu, Grigorios G. Chrysos, Pablo M. Olmos, Volkan Cevher

I am now member of the ELLIS society

Variational Mixture of HyperGenerators for Learning Distributions Over Functions. Batuhan Koyuncu, Pablo Sanchez-Martin, Ignacio Peis, Pablo M. Olmos, Isabel Valera