01 / IntroductionA Coruña, Spain

Machine learning · A Coruña, Spain

Bruno Corcuera.

I work on world models, visual representations, and learned dynamics for prediction and control.

Doctoral Researcher at LIDIA, Universidade da Coruña, supervised by Brais Cancela.

Publications GitHub Contact

02 / Publications

Publications

NeurIPS 2026Main Track Poster

Space-Aware World Models:
Spatial Persistence Through Factored Scene Representations

Bruno Corcuera, Carlos Eiras-Franco, Brais Cancela

SWM separates persistent scene structure from agent dynamics, keeping places consistent across long imagined trajectories. It synthesizes views in unseen layouts. Evaluations in 3D navigation and continuous control show stronger revisitation consistency, geometric fidelity and control-relevant predictions.

+ detailsComing soon

LIDIA · Universidade da Coruña · CITIC

03 / Background

Background

Oct 2026 —Present

Doctoral Researcher

LIDIA · Universidade da Coruña
PhD in Machine Learning · Supervisor: Brais Cancela

Research on world models and efficient generative models.

Apr 2025 —Sep 2026

Research Assistant

LIDIA · Universidade da Coruña

Research on representation learning and dynamic feature selection for efficient visual deep learning models.

2025 — 26

MSc in Business Intelligence & Big Data in Secure Environments

Universities of Burgos, León & Valladolid

Master’s thesis on a local generative-AI assistant for pedagogical code review.

Sep 2024 —Feb 2025

Data Scientist Intern

Inditex

Worked on large-scale sales forecasting and production ML pipelines. Built training and deployment workflows using Snowflake, Azure ML, Azure DevOps, Spark and Databricks, including distributed training.

2021 — 25

BSc in Data Science & Engineering

Universidade da Coruña

Thesis on perceptual latent representations for world models. Awarded honours.Thesis record

04 / Research & code

Research & code

Selected research projects and implementations related to world models and representation learning.

Space-Aware World Models (SWM)

NeurIPS 2026 · world models · spatial representations

Factored scene representations for spatially coherent rollouts and novel environment synthesis.

PaperCodeComing soon

Perceptual Latent Representations for World Models

Research project · representation learning · world models

Learning compact perceptual representations for improved reconstruction, learned dynamics and downstream control.

Paper Code

World Models in PyTorch

Implementation · world models

End-to-end PyTorch implementation of World Models with VAE vision, MDN-RNN dynamics and CMA-ES control.

Code

All repositories

05 / Contact

Contact

bruno.sanchez1@udc.es

Personal email: brunocorcueras@gmail.com

X LinkedIn GitHub LIDIA