13 papers
TASSO: TAsk-Specific Subspace Optimization for Continual Learning of Vision-Language Models
Chang Sun, Francesco Barbato, Matteo Caligiuri +1
Vision-Language Models (VLMs) exhibit strong zero-shot capabilities, making them an attractive solution for continual learning across diverse tasks. However, during continual adapt…
EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models
Matteo Caligiuri, Francesco Barbato, Pietro Zanuttigh +1
Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training. Nevertheless, increasing model sizes impose subs…
Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis
Federico Lincetto, Gianluca Agresti, Mattia Rossi +2
Neural rendering techniques allow for accurate reconstruction of the geometry and color appearance of 3D scenes. Some methods have extended their use to additional imaging modaliti…
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…
Split&Splat: Zero-Shot Panoptic Segmentation via Explicit Instance Modeling and 3D Gaussian Splatting
Leonardo Monchieri, Elena Camuffo, Francesco Barbato +2
3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framewo…
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…