PhD student · University of Barcelona

Imanol G. Estepa

I work on unified self-supervised learning: models that learn useful visual representations while keeping the ability to generate, reconstruct, and reason about images.

Supervised by Prof. Petia Radeva, my research explores representation learning, generative modeling, semantic tokenization, and interpretable latent spaces.

Interactive research pages

Start with the visual versions.

Open the project gallery

Latest

Recent notes.

[Paper] LEASE was accepted at CVPR 2026.
[Workshop] Co-organized Dishcovery Mission II at MetaFood CVPR'26, receiving more than 1.5k submissions.
[Paper] Sorcen was accepted at WACV 2026 on the first round.
[Teaching] Co-organized the 2nd Seasonal International School at UB on Demystifying AI.
[Workshop] Co-organized the Dishcovery VLM Challenge at MetaFood CVPR'25.

Publications

Research trail.

Scholar profile

Academic life

Service and talks.

2025+ CVPR and ICCV reviewer.

2024+ WACV reviewer.

2023+ IEEE Transactions on Multimedia reviewer.

2023 Talk at DLBCN, with public recording and slides.

2023 Master's thesis completed with honours: Analysis and improvement proposal on self-supervised deep learning.