3 papers
cs.LG2026
On the Interaction Between Model Compression and Test-Time Adaptation
Francesco Corti, Dong Wang, Young D. Kwon +2
Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation…
cs.LG2025
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…
cs.LG2023
REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints
Francesco Corti, Balz Maag, Joachim Schauer +2
Deep learning models deployed on edge devices frequently encounter resource variability, which arises from fluctuating energy levels, timing constraints, or prioritization of other…