Gabriel Moreira
I’m a PhD student at LTI-CMU and ISR-IST, under a CMU Portugal scholarship. I’m fortunate to be advised by João Paulo Costeira (IST), Manuel Marques (IST) and Chenyan Xiong (CMU). My research focuses on the intersection between vision and language, with an emphasis on representation learning for recognition and generation. During the summer of 2024, I joined Meta Reality Labs as a research scientist intern. Prior to my PhD, I worked on pose graph optimization and spent six months as a research intern at Airbus.
I’ve served as reviewer for AAAI, ICRA, CVPR, ICLR and ICML (Gold reviewer 2026).
news
| Jun 23, 2026 | I’ll be at ICML 2026 in Seoul, South Korea, presenting my paper: Spectral Guidance for Efficient and Flexible Control of Diffusion Models. |
|---|---|
| Jan 22, 2025 | I’ll be at AISTATS 2025 in Mai Khao, Thailand, presenting our paper Learning Visual Semantic Subspace Representations. |
| Jun 03, 2024 | I’ve join Meta Reality Labs as a research scientist intern! |
| May 13, 2024 | I’ll be in Yokohama, at ICRA 2024, presenting VICAN. |
| Jan 01, 2024 | I’ll be at WACV 2024, in Waikoloa, presenting our paper on Hyperbolic vs Euclidean embeddings in few-shot learning. |
publications
- Native Hierarchical and Compositional Representations with Subspace EmbeddingsIn Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2 , 2026
- Spectral Guidance for Flexible and Efficient Control of Diffusion ModelsIn International Conference on Machine Learning , 2026