This paper introduces a novel boundary testing approach for deep learning systems, combining SUT feedback with controlled latent space manipulations. Unlike prior methods, Mimicry uses style-based GANs to enable precise, goal-driven test case generation.
I’m excited to share that the paper “Fertility During Learning In Evolutionary Robot Systems” lead by Jacopo Michele Di Matteo and co-authored by Prof. Dr. Guszti Eiben and myself has been accepted at GECCO 2025, one of the top ranking conferences in evolutionary computing. This work investigates the performance differences when adapting fertility conditions for evolvable robots.
[Update 20.01.2025] I am happy to announce that this work has been accepted to QCNC 2025 as a short paper. The abstract in this post is now adjusted to the Conference Paper. For the previous version look at the arXiv paper. [Original 06.09.2024] For my MSc thesis with the AMLab, I embarked on my first exploration into quantum computing, focusing on Quantum Error Correction (QEC). My supervisor, Evgenii Egorov, suggested this topic, building on his research on Equivariant Decoders for QEC. I...
I worked with Dr. Kevin Godin-Dubois on realising a concept towards ‘Artificial General Creatures’. This work was presented as part of the Evolution of Things workshop at ALife2024. My main contributions were to implement hardware access on the physical modular robots to transfer the learned controller from simulation to reality. Abstract: We introduce here the concept of Artificial General Creatures (AGC) which encompasses “robotic or virtual agents with a wide enough range of capabilit...
During my time as Research Assistant at the CI-Group @ VU Amsterdam, I worked with Dr. Jie Luo on a study investigating Lamarckian Inheritance in Modular Robots. My main contribution was replicating the simulator experiments with real robots, allowing for better understanding of behavior and sim2real gap.