5 papers
The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching
Dong Wang, Wenwu Tang, Francesco Corti +3
Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introduce the Golden Path Hypothesis…
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…
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…
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…
Studying the impact of magnitude pruning on contrastive learning methods
Francesco Corti, Rahim Entezari, Sara Hooker +2
We study the impact of different pruning techniques on the representation learned by deep neural networks trained with contrastive loss functions. Our work finds that at high spars…