4 papers
From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices
Georg Slamanig, Francesco Corti, Olga Saukh
Parameter-efficient fine-tuning (PEFT) methods reduce the computational costs of updating deep learning models by minimizing the number of additional parameters used to adapt a mod…
APEX: Automated Parameter Exploration for Low-Power Wireless Protocols
Mohamed Hassaan M. Hydher, Markus Schuss, Olga Saukh +2
Careful parametrization of networking protocols is crucial to maximize the performance of low-power wireless systems and ensure that stringent application requirements can be met.…
FocusDD: Real-World Scene Infusion for Robust Dataset Distillation
Youbing Hu, Yun Cheng, Olga Saukh +4
Dataset distillation has emerged as a strategy to compress real-world datasets for efficient training. However, it struggles with large-scale and high-resolution datasets, limiting…
Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection
Jakob Shack, Katarina Petrovic, Olga Saukh
Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates t…