11 papers
INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference
Ahmed Å abanoviÄ, Paul Joe Maliakel, Ivona BrandiÄ
Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but incurs communication delay and…
An Online Approach for Entanglement Verification Using Classical Shadows
Marwa Marso, Sabrina Herbst, Jadwiga Wilkens +3
Quantum measurements are slow, while classical processors are fast, yet existing hybrid protocols never exploit this asymmetry. In this work, we propose an alternative formulation…
Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling
Paul Joe Maliakel, Shashikant Ilager, Ivona Brandic
LLM inference exhibits substantial variability across queries and execution phases, yet inference configurations are often applied uniformly. We present a measurement-driven charac…
Limits of quantum generative models with classical sampling hardness
Sabrina Herbst, Ivona BrandiÄ, Adrián Pérez-Salinas
Sampling tasks have been successful in establishing quantum advantages both in theory and experiments. This has fueled the use of quantum computers for generative modeling to creat…
Clustered Federated Learning with Hierarchical Knowledge Distillation
Sabtain Ahmad, Meerzhan Kanatbekova, Ivona Brandic +1
Clustered Federated Learning (CFL) has emerged as a powerful approach for addressing data heterogeneity and ensuring privacy in large distributed IoT environments. By clustering cl…
Qubit-Efficient QUBO Formulation for Constrained Optimization Problems
Meerzhan Kanatbekova, Vincenzo De Maio, Ivona Brandic
Quantum computing has emerged as a promising alternative for solving combinatorial optimization problems. The standard approach for encoding optimization problems on quantum proces…