Sotabase

Career

· Staff Research Scientist - AI Agent Security (Lakera), Check Point Software2025–
· Senior Research Scientist, Lakera2024–2025
· Senior Research Scientist, Waymo2019–2024
· Research Scientist, Latent Logic2017–2019
· Visiting Researcher, University of Oxford2017–2018
· PHD Candidate, University of Amsterdam2014–2018
· Intern, Toshiba Medical Visualization Systems (Europe) Ltd2013–2013
· Research Assistant, National University of San Juan2012–2012
· Master of Engineering (MEng), Informatics, Merit, University of Cambridge2009–2013

Publications (15)

Fast Context Adaptation via Meta-Learning
International Conference on Machine Learning · 2018
410
cited
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
International Conference on Learning Representations · 2019
306
cited
Inverse Reinforcement Learning from Failure
Adaptive Agents and Multi-Agent Systems · 2016
102
cited
TACO: Learning Task Decomposition via Temporal Alignment for Control
International Conference on Machine Learning · 2018
101
cited
Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation
IEEE International Conference on Robotics and Automation · 2022
80
cited
Learning From Demonstration in the Wild
IEEE International Conference on Robotics and Automation · 2018
78
cited
VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning
Journal of machine learning research · 2021
58
cited
CAML: Fast Context Adaptation via Meta-Learning
arXiv.org · 2018
38
cited
TERESA: a socially intelligent semi-autonomous telepresence system
2015
32
cited
Rapidly exploring learning trees
IEEE International Conference on Robotics and Automation · 2017
27
cited
Acquiring social interaction behaviours for telepresence robots via deep learning from demonstration
IEEE/RJS International Conference on Intelligent RObots and Systems · 2017
9
cited
Gandalf the Red: Adaptive Security for LLMs
International Conference on Machine Learning · 2025
3
cited
Hierarchical Imitation Learning for Stochastic Environments
IEEE/RJS International Conference on Intelligent RObots and Systems · 2023
3
cited
AIMS CDT Project Report : Towards One-Shot Learning From Demonstration via Reinforcement Learning
2018
A Safety and Security Framework for Real-World Agentic Systems
arXiv.org · 2025
Sotabase
Kyriacos Shiarlis | Researcher Profile | Sotabase | Sotabase