Background images generated with openai.com and freepik.com

About Themis

The goal of Themis project is to devise fundamentals for the new groundbreaking generation of geographically distributed probabilistic operating systems unifying computation and communication facilities. The idea is to instantly offload arbitrary portions of the code from the end device (like the IoT sensors) to the arbitrary computational surrogates that might be an idle node, your personal laptop, a raspberry pi or any other computational facility. The challenge is to achieve sustainability, while facilitating low latency of hyper heterogeneous, highly volatile tactile Internet applications. Our ambitions in Themis are enabled by the recent developments in Edge computing, a new concept bringing computation and data storage closer to the location where it is needed and by probabilistic large scale near real time systems relying on Markov Chains -- both areas pioneered by the PI. Besides very concrete use cases within intelligent traffic management and hybrid classic/quantum architectures, we identified the innovation potential in the area of Microgrids and Earth Science.

Funded by:

Partners

Thomas Monz

Universität Innsbruck - Austria

Ewa Deelman

University of Southern California - USA

Publications

2026

  • Ahmed Šabanović, Paul Joe Maliakel, and Ivona Brandić. "INAR-VL: Input-Aware Routing for Edge–Cloud Vision–Language Inference. EdgeSys 2026 in conjuction with MobiSys 2026, 25th June 2026, Cambridge, UK."
  • Marwa Marso, Sabrina Herbst, Jadwiga Wilkens, Vincenzo De Maio, Ivona Brandić and Richard Kueng. "An Online Approach for Entanglement Verification Using Classical Shadows". pdf doi
  • Thomas Ziller, Shashikant Ilager, Alessandro Tundo, Ezio Bartocci, Leonardo Mariani, Ivona Brandic: GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference. CoRR abs/2601.17551 pdf
  • Paul Joe Maliakel, Shashikant Ilager, Ivona Brandić. "Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling" in The 26th IEEE International Symposium on Cluster, Cloud, and Internet Computing 18–21 May 2026, Sydney, Australia. [BEST STUDENT PAPER AWARD NOMINEE] pdf

2025

  • Josip Zilic, Vincenzo De Maio, Shashikant Ilager, Ivona Brandic: FRESCO: Fast and Reliable Edge Offloading With Reputation-Based Hybrid Smart Contracts. IEEE Trans. Serv. Comput. 18(6): 3810-3823 (2025) doi
  • Sabtain Ahmad, Meerzhan Kanatbekova, Ivona Brandic, Atakan Aral: Clustered Federated Learning with Hierarchical Knowledge Distillation. CoRR abs/2512.10443 (2025) doi pdf
  • Kanatbekova, M., De Maio, V., Brandic, I. (2025) "Qubit-Efficient QUBO Formulation for Constraint Optimization Problems". (preprint) pdf
  • Sabrina Herbst, Ivona Brandić, Adrián Pérez-Salinas. "Limits of quantum generative models with classical sampling hardness" https://arxiv.org/abs/2512.24801 doi
  • Sabtain Ahmad, Thomas Schneidergruber, Ivona Brandić, and Johannes Scholz. "On-Device Federated Learning for Remote Alpine Livestock Monitoring" in International European Conference on Parallel and Distributed Computing (accepted, to appear). doi pdf
  • Felix Zilk, Alessandro Tundo, Vincenzo De Maio, and Ivona Brandic. "Breaking Down Quantum Compilation: Profiling and Identifying Costly Passes" IEEE International Workshop on Quantum Computing: Circuits Systems Automation and Applications (QC-CSAA) (co-located with ISVLSI Symposium) [BEST PAPER AWARD] pdf doi
  • Alessandro Tundo, Federica Filippini, Francesco Regonesi, Michele Ciavotta, and Marco Savi, "Decentralized Edge Workload Forecasting With Gossip Learning" in IEEE Transactions on Network and Service Management pdf doi

2024

  • Daniel May, Alessandro Tundo, Shashikant Ilager, and Ivona Brandic. Towards Energy-Efficient Split Computing: A Hardware-Software Co-Design Perspective, 20th European Conference on Computer Systems (EuroSys), March 30 - April 3, 2025, Rotterdam, The Netherlands. [Poster Paper] pdf poster
  • Shashikant Ilager, Lukas Florian Briem and Ivona Brandic. GREEN-CODE: Learning Energy Efficient Code Generation in LLMs, 2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid), May 19-22 2025, Tromso, Norway. preprint
  • Vincenzo De Maio, Ivona Brandic, Ewa Deelman, Jürgen Cito: The Road to Hybrid Quantum Programs: Characterizing the Evolution from Classical to Hybrid Quantum Software QSE-NE (co-located with ESEC/FSE 2025) pdf
  • S. Ilager, J. Fahringer, A. Tundo. A Decentralized and Self-Adaptive Approach for Monitoring Volatile Edge Environments. To appear in TAAAs pdf
  • Sabrina Herbst, Vincenzo de Maio, Ivona Brandic, "On Optimizing Hyperparameters for Quantum Neural Networks," 2024 IEEE International Conference on Quantum Computing and Engineering (QCE), Montreal, QC, Canada, 2024, pp. 1478-1489 pdf doi
  • Auday Al-Dulaimy, Matthijs Jansen, Bjarne Johansson, Animesh Trivedi, Alexandru Iosup, Mohammad Ashjaei, Antonino Galletta, Dragi Kimovski, Radu Prodan, Konstantinos Tserpes, George Kousiouris, Chris Giannakos, Ivona Brandic, Nawfal Ali, Andre B. Bondi, Alessandro V.Papadopoulos. The Computing Continuum: From IoT to the Cloud. Internet of Things, Springer. pdf
  • Herbst S., Cranganore S.S., De Maio V., and Brandic I. Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks. The Thirteenth International Conference on Learning Representations. 2025 (to appear). pdf doi
  • Meerzhan Kanatbekova, Shashikant Ilager, Ivona Brandic. ABBA-VSM: Time Series Classification using Symbolic Representation on the Edge. ICSOC 2024: International Conference on Service-Oriented Computing Tunis, Tunisia, December 3-6, 2024. pdf
  • Xiaoyu Chu, Daniel Hofstätter, Shashikant Ilager, Sacheendra Talluri, Duncan Kampert, Damian Podareanu, Dmitry Duplyakin, Ivona Brandic, Alexandru Iosup. Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis. The 30th International Conference on Parallel and Distributed Systems (ICPADS 2024), Belgrade, Serbia, October 10-14, 2024. pdf
  • Vincenzo De Maio, Dominik Bork and Ivona Brandic. RIGOLETTO: A Workflow Definition Language for Hybrid Quantum-Classical Scientific Applications. 26th IEEE Int'l Conference on Business Informatics (CBI) 2024. pdf
  • Sandeep Suresh Cranganore, Vincenzo De Maio, Ivona Brandic, Ewa Deelman. Paving the Way to Hybrid Quantum-Classical Scientific Workflows. Future Generation Computer Systems 2024 (to appear). pdf
  • Alessio Catalfamo, Atakan Aral, Ivona Brandic, Ewa Deelman, and Massimo Villari. Machine Learning Workflows in the Computing Continuum for Environmental Monitoring. 24th International Conference on Computational Science (ICCS), 2-4 July 2024, Malaga, Spain. pdf
  • Shashikant Ilager, Daniel Balouek, Sidi Mohammed Kaddour, Ivona Brandic. Proteus: Towards Intent-driven Automated Resource Management Framework for Edge Sensor Nodes. 14th Workshop on AI and Sceientific Computing at Scale using Flexible Computing Infrastructures (FlexScience 2024), in conjunction with HPDC 2024, Pisa, Italy, June 3-4, 2024. pdf
  • Paul Joe Maliakel, Shashikant Ilager, Ivona Brandic, "FLIGAN: Enhancing Federated Learning with Incomplete Data using GAN," In the ACM 7th International Workshop on Edge Systems, Analytics and Networking (EdgeSys24)(EuroSys24), Athens, Greece, 22nd April, 2024. pdf

2023

  • Shashikant Ilager, Adel N. Toosi, Mayank Raj Jha, Ivona Brandic, Rajkumar Buyya. A Data-driven Analysis of a Cloud Data Center: Statistical Characterization of Workload, Energy and Temperature. The 16th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2023). Taormina (Messina), Italy, 4-7 December 2023 (to appear). Best Paper Award pdf
  • Sabtain Ahmad, Halit Uyanık, Tolga Ovatman, Mehmet Tahir Sandıkkaya, Vincenzo De Maio, Ivona Brandic, Atakan Aral. Sustainable Environmental Monitoring via Energy and Information Efficient Multi-Node Placement. IEEE Internet of Things Journal DOI: 10.1109/JIOT.2023.3303124 pdf
  • Alessandro Tundo, Marco Mobilio, Shashikant Ilager, Ivona Brandic, Ezio Bartocci, Leonardo Mariani. An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge. 38th IEEE/ACM International Conference on Automated Software Engineering (ASE2023), Sep 11, 2023 - Sep 15, 2023, Luxembourg. pdf
  • Sabrina Herbst, Vincenzo de Maio, Ivona Brandic. Streaming IoT Data and the Quantum Edge: A Classic/Quantum Machine Learning Use Case. International Workshop on Urgent Analytics for Distributed Computing, August 28/29 2023, Limassol, Cyprus (collocated with Euro-Par 2023). (to appear) pdf doi
  • Shashikant Ilager, Vincenzo De Maio, Ivan Lujic, and Ivona Brandic. Data-centric Edge-AI: A Symbolic Representation Use Case. IEEE Symposium on Intelligent Edge Computing and Communications (iEDGE), July 6-7, 2023, Chicago, USA. pdf
  • Daniel Hofstätter, Shashikant Ilager, Ivan Lujic, Ivona Brandic. SymED: Adaptive and Online Symbolic Representation of Data on the Edge. 29th International European Conference on Parallel and Distributed Computing, 28 August - 1 September 2023 Limassol, Cyprus. Chair's appreciation award for junior researcher pdf
  • Vincenzo De Maio, Meerzhan Kanatbekova, Felix Zilk, Nicolai Friis, Tobias Guggemos, and Ivona Brandic. Training Computer Scientists for the Challenges of Hybrid Quantum-Classical Computing. The 24th IEEE/ACM international Symposium on Cluster, Cloud and Internet Computing. Philadelphia, May 6-9, 2024, pp 626 - 635. pdf

Team - TU Wien Computational Sustainability Group

Univ. Prof. Dr.

Ivona Brandić

Project leader
Dipl.-Ing.

Jakob Fahringer

Project assistant
B.Sc.

Daniel Hofstätter

Project assistant
M.Sc.

Meerzhan Kanatbekova

Project assistant
M.Sc.

Josip Žilić

Project assistant
Dipl.-Ing.

Daniel May

Project assistant
Dipl.-Ing.

Thomas Ziller

Research Assistant
Dipl.-Ing.in

Sabrina Herbst

PhD Student