Manuel Goulão
  • home
  • blog
  • CV
  • research
  • about
Research
My current research is focused on improving Deep Learning data-efficiency and generalization through self-supervised learning and distillation. I am particularly interested in the use of such techniques to deploy in real-world applications. In my job at NeuralShift, I am focused in the intersection of NLP with the legal domain.
Papers
Gymnasium: A Standard Interface for Reinforcement Learning Environments Mark Towers, Ariel Kwiatkowski, Jordan Terry, John U. Balis, Gianluca De Cola, Tristan Deleu, Manuel Goulão, Andreas Kallinteris, Markus Krimmel, Arjun KG, Rodrigo Perez-Vicente, Andrea Pierré, Sander Schulhoff, Jun Jet Tai, Hannah Tan, Omar G. Younis arXiv under review
Training environmental sound classification models for real-world deployment in edge devices Manuel Goulão, Lourenço Bandeira, Bruno Martins, Arlindo L. Oliveira Discover Applied Sciences 26 March 2024 Environmental Science, Computer Science, Engineering Discover Applied Sciences
Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning Manuel Goulão and Arlindo L. Oliveira ECAI 2023 code arxiv