// research
11 papers 7 peer-reviewed 1 open-source project
Original
Fine layers
Medium layers
Coarse layers
Target
I started a new open-source project: Context Garden, a collection of self-contained Agent Skills that cut an agent’s context usage. The skills are deterministic, run fully offline, and make no LLM calls inside the tooling itself. They ar...
In this work, we study how well Large Language Models translate code between programming languages and how well they repair their own translation errors. We present CodeTransBenchmark, a framework for evaluating LLM-based translation and...
In this work, we bring generative test input generation to the audio domain. Instead of perturbing waveforms directly, GATAS operates in the phoneme-level latent space of a text-to-speech model, producing failure-inducing inputs for auto...
[Update 12.04.2026] Our paper is now published in the Proceedings of the 7th IEEE/ACM International Workshop on Deep Learning for Testing and Testing for Deep Learning (DeepTest ‘26). The preprint remains available on arXiv.
In this work, we examine how models behave under isolated semantic changes by directly manipulating individual features in StyleGAN’s S-space, instead of entangled Z or W representations. This enables precise, feature-level testing and h...
This paper introduces a novel Diffusion based testing approach for deep learning systems, combining SUT feedback with weight adaptations in HyperNets. Unlike prior methods, HyNeA does not rely on curated datasets, making it more flexible...
[Update 28.09.2025] I am happy to announce, that our paper was accepted for publication in TOSEM. [Original 11.05.2025] This paper introduces a novel boundary testing approach for deep learning systems, combining SUT feedback with contr...
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 c...
[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.
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...
[Update 08.2026] I am happy to announce that this work is now published in IEEE Transactions on Evolutionary Computation (Vol. 30, No. 4, 2026).
I`m happy to announce that my first paper Morphological-Novelty in Modular Robot Evolution, has been accepted for presentation at the IEEE SSCI Conference 2023 in Mexico-City. This paper was based on my BSc Thesis, supervised by Prof. Dr...
