Kostas Balaskas

  • Haid-und-Neu-Str. 7
    Bldg. 07.21
    76131 Karlsruhe

Kostas Balaskas received a B.Sc. degree in Physics and M.Sc. degree in Electronics/Communications from the Aristotle University of Thessaloniki in 2018 and 2020, respectively. He joined the Karlsruhe Institute of Technology in October 2021 as a research assistant. Since July 2022, he is pursuing his PhD as a research assistant in the Chair for Embedded Systems.


Konstantinos Balaskas, Andreas Karatzas, Christos Sad, Kostas Siozios, Iraklis Anagnostopoulos, Georgios Zervakis, Jörg Henkel
Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization
in IEEE Transactions on Emerging Topics in Computing, DOI, PDF, Early Access 2024.
Nikolay Penkov; Konstantinos Balaskas; Martin Rapp; Jörg Henkel
Differentiable Slimming for Memory-Efficient Transformers
in IEEE Embedded Systems Letters (volume 15, Issue 4), DOI, PDF, Dec 2023.
Konstantinos Balaskas, Florian Klemme, Georgios Zervakis, Kostas Siozios, Hussam Amrouch, Jörg Henkel
Variability-Aware Approximate Circuit Synthesis via Genetic Optimization
in IEEE Transactions on Circuits and Systems I: Regular Papers (Volume 69, Issue 10), DOI, PDF, Oct 2022.
Konstantinos Balaskas, Georgios Zervakis, Hussam Amrouch, Jörg Henkel, Kostas Siozios
Automated Design Approximation to Overcome Circuit Aging
in IEEE Transactions on Circuits and Systems I: Regular Papers (Volume 68, Issue 11), DOI, PDF, Nov 2021.
Konstantinos Balaskas, Georgios Zervakis, Kostas Siozios, Mehdi B. Tahoori, Jörg Henkel
Approximate Decision Trees For Machine Learning Classification on Tiny Printed Circuits
in 23rd International Symposium on Quality Electronic Design (ISQED '22), DOI, PDF, 6-8 April 2022.
Kilian Pfeiffer, Konstantinos Balaskas, Kostas Siozios, Jörg Henkel
Energy-Aware Heterogeneous Federated Learning via Approximate Systolic DNN Accelerators
in arxiv, DOI, PDF, 2024.

Student Theses

Finished Projects
NameType of workTitleMentorCompletion date
Penkov, NikolayMaster thesisSlimmable Neural NetworksBalaskas, Kostas / Rapp, Martin2023-05-08