Adriana Romero-Soriano
About
Appointed Canada CIFAR AI Chair – 2023
Adriana Romero-Soriano is a research scientist at FAIR (Meta AI), an adjunct professor at McGill University, a core industry member of Mila and a Canada CIFAR AI Chair. Romero-Soriano’s research focuses on developing machine learning models which can learn from multi-modal data, reason about conceptual relations, and leverage active and adaptive data acquisition strategies. The goal of her research is to enable interactive and immersive experiences of content creation and reconstruction that work for everyone. Her most recent work intersects generative modeling, active sensing, and responsible AI.
Awards
- Best paper award, CVPR Workshop on Computer Vision in Vehicle Technology (2017)
- Best paper award, CVPR Deep-vision workshop (2016)
Relevant Publications
- Casanova, A., Careil, M., Verbeek, J., Drozdzal, M., & Romero-Soriano, A. (2021). “Instance- Conditioned GAN.” In Advances in Neural Information Processing Systems (NeuRIPS), vol. 34, pp. 27517—27529.
- Smith, E., Meger, D., Pineda, L., Calandra, R., Malik, J., Romero-Soriano, A., & Drozdzal, M. (2021). “Active 3D Shape Reconstruction from Vision and Touch.” In Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 16064—16078.
- Zhang, Z., Romero, A., Muckley, M. J., Vincent, P., Yang, L., & Drozdzal, M. (2019). “Reducing Uncertainty in Undersampled MRI Reconstruction With Active Acquisition.” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2049—2053.
- Velickovic, P., Cucurull, G., Casanova , A., Romero, A., Lio, P., & Bengio, Y. (2017). “Graph attention networks.” 6th International Conference on Learning Representations (ICLR).
- Romero, A., Ballas, N., Ebrahimi Kahou, S., Chassang, A., Gatta, C., & Bengio, y. (2015). “Fitnets: Hints for thin deep nets.” 3rd International Conference on Learning Representations (ICLR). Profile Link (two max) – e.g. your own webpage, Research Gate, Google Scholar: https://scholar.google.com/citations?user=Sm15FXIAAAAJ&hl=en