20 citations · 24 across the 8 of their papers we have counts for
10 papers
Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures
Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni +3
Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a significant attack surface, as ma…
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
Donald Shenaj, Federico Errica, Antonio Carta
Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since…
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
Donald Shenaj, Ondrej Bohdal, Taha Ceritli +3
On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address…
FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
Matteo Caligiuri, Francesco Barbato, Donald Shenaj +2
Federated Learning (FL) is an established paradigm for training deep learning models on decentralized data. However, as the size of the models grows, conventional FL approaches oft…
LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
Donald Shenaj, Ondrej Bohdal, Mete Ozay +2
Recent advancements in image generation models have enabled personalized image creation with both user-defined subjects (content) and styles. Prior works achieved personalization b…
When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather
Giulia Rizzoli, Matteo Caligiuri, Donald Shenaj +2
In Federated Learning (FL), multiple clients collaboratively train a global model without sharing private data. In semantic segmentation, the Federated source Free Domain Adaptatio…
Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers
Giulia Rizzoli, Donald Shenaj, Pietro Zanuttigh
With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest. However, ground truth data for semanti…
Asynchronous Federated Continual Learning
Donald Shenaj, Marco Toldo, Alberto Rigon +1
The standard class-incremental continual learning setting assumes a set of tasks seen one after the other in a fixed and predefined order. This is not very realistic in federated l…
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
Donald Shenaj, Eros Fanì, Marco Toldo +6
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the co…
Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation
Donald Shenaj, Francesco Barbato, Umberto Michieli +1
Deep neural networks are typically trained in a single shot for a specific task and data distribution, but in real world settings both the task and the domain of application can ch…