Suivre
Miguel Vasco
Miguel Vasco
Postdoctoral Researcher KTH Royal Institute of Technology
Adresse e-mail validée de kth.se - Page d'accueil
Titre
Citée par
Citée par
Année
Project INSIDE: towards autonomous semi-unstructured human–robot social interaction in autism therapy
FS Melo, A Sardinha, D Belo, M Couto, M Faria, A Farias, H Gamboa, ...
Artificial intelligence in medicine 96, 198-216, 2019
542019
Geometric multimodal contrastive representation learning
P Poklukar*, M Vasco*, H Yin, FS Melo, A Paiva, D Kragic
International Conference on Machine Learning, 17782-17800, 2022
512022
Playing games in the dark: An approach for cross-modality transfer in reinforcement learning
R Silva, M Vasco, FS Melo, A Paiva, M Veloso
Proceedings of the 19th International Conference on Autonomous Agents and …, 2020
162020
Leveraging hierarchy in multimodal generative models for effective cross-modality inference
M Vasco, H Yin, FS Melo, A Paiva
Neural Networks 146, 238-255, 2022
152022
MHVAE: a human-inspired deep hierarchical generative model for multimodal representation learning
M Vasco, FS Melo, A Paiva
arXiv preprint arXiv:2006.02991, 2020
122020
3D map distribution of metallic nanoparticles in whole cells using MeV ion microscopy
M Vasco, LC Alves, V Corregidor, D Correia, CP Godinho, I SÁ‐CORREIA, ...
Journal of Microscopy 267 (2), 227-236, 2017
72017
How to sense the world: Leveraging hierarchy in multimodal perception for robust reinforcement learning agents
M Vasco, H Yin, FS Melo, A Paiva
Proceedings of the 21st International Conference on Autonomous Agents and …, 2022
62022
Learning multimodal representations for sample-efficient recognition of human actions
M Vasco, FS Melo, DM de Matos, A Paiva, T Inamura
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
52019
Explainable agency by revealing suboptimality in child-robot learning scenarios
S Tulli, M Couto, M Vasco, E Yadollahi, F Melo, A Paiva
International Conference on Social Robotics, 23-35, 2020
42020
Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning
PP Santos, DS Carvalho, M Vasco, A Sardinha, PA Santos, A Paiva, ...
arXiv preprint arXiv:2210.06274, 2022
22022
Exploiting symmetry in human robot-assisted dressing using reinforcement learning
P Ildefonso, P Remédios, R Silva, M Vasco, FS Melo, A Paiva, M Veloso
Progress in Artificial Intelligence: 20th EPIA Conference on Artificial …, 2021
22021
Will You Participate? Exploring the Potential of Robotics Competitions on Human-Centric Topics
Y Zhang, M Vasco, M Björkman, D Kragic
International Conference on Human-Computer Interaction, 240-255, 2024
12024
Multimodal representation learning for robotic cross-modality policy transfer
M Vasco
Proceedings of the 19th International Conference on Autonomous Agents and …, 2020
12020
Online Motion Concept Learning: A Novel Algorithm for Sample-Efficient Learning and Recognition of Human Actions.
M Vasco, FS Melo, DM de Matos, A Paiva, T Inamura
AAMAS, 2244-2246, 2019
12019
3D map of the distribution of metals in a cell: applications to the toxicity of nanoparticles
M Vasco
Master Thesis, Instituto Superior Técnico, Universidade de Lisboa. Available …, 2016
12016
Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks
A Reichlin, G Tegnér, M Vasco, H Yin, M Björkman, D Kragic
arXiv preprint arXiv:2410.01476, 2024
2024
A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo
M Vasco*, T Seno*, K Kawamoto, K Subramanian, PR Wurman, P Stone
arXiv preprint arXiv:2406.12563, 2024
2024
Can Foundation Models Smell Like Humans?
F Taleb, M Vasco, N Rajabi, M Björkman, D Kragic
ICLR 2024 Workshop on Representational Alignment, 2024
2024
NeuralThink: Algorithm Synthesis that Extrapolates in General Tasks
B Esteves, M Vasco, FS Melo
arXiv preprint arXiv:2402.15393, 2024
2024
Goal-Conditioned Offline Reinforcement Learning via Metric Learning
A Reichlin, M Vasco, H Yin, D Kragic
arXiv preprint arXiv:2402.10820, 2024
2024
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20