Scholar
Gabriel Leivas Oliveira
Google Scholar ID: 5anRZEcAAAAJ
Lecturer in AI, University of Bristol
Citations & Impact
Citations
1,188
H-index
13
i10-index
16
Publications
20
Co-authors
31
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications:
- - Medeiros, H., Sharifi-Noghabi, H., Oliveira, G., Irandoust S. 'Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting', PUT ICML 2025.
- - Chen, C., Oliveira, G., Sharifi-Noghabi, H., Sylvain T.; 'LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modeling', TMLR 2025.
- - Wonho Bae, Danica J. Sutherland, Gabriel L. Oliveira, 'Uncertainty Herding: One Active Learning Method for All Label Budgets', ICLR 2025.
- - Wonho Bae, Yi Ren, Mohamed Osama Ahmed, Frederick Tung, Danica J. Sutherland, Gabriel L. Oliveira, 'AdaFlood: Adaptive Flood Regularization', TMLR 2024.
- - Vani, A; Tung, F; Oliveira G; Sharifi H. 'Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics', ICML 2024.
Research Experience
- Machine Learning Researcher and later Team Lead at Borealis AI Vancouver from February 2019 to March 2025.
Education
- PhD in Computer Science, 2014 - 2019, University of Freiburg, supervised by Professors Thomas Brox and Wolfram Burgard; Master of Science in Computer Science, 2014, University of Minnesota; Master of Science in Computer Science, 2012, Federal University of Minas Gerais; Bachelor of Science in Computer Engineering, 2009, Federal University of Rio Grande.
Background
- Lecturer in Artificial Intelligence at the School of Engineering Mathematics and Technology from the University of Bristol and an ELLIS member. Main research interests include deep learning, robust machine learning, computer vision, and robotics perception.
Miscellany
- Interests include robust machine learning, federated learning, multi-task learning, semantic segmentation, computer vision, and robotics perception.
