565 citations · 663 across the 57 of their papers we have counts for
7 papers · 2 filters
Task Singular Vectors: Reducing Task Interference in Model Merging
Antonio Andrea Gargiulo, Donato Crisostomi, Maria Sofia Bucarelli +3
Task Arithmetic has emerged as a simple yet effective method to merge models without additional training. However, by treating entire networks as flat parameter vectors, it overloo…
ATM: Improving Model Merging by Alternating Tuning and Merging
Luca Zhou, Daniele Solombrino, Donato Crisostomi +3
Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In thi…
TOAST: Transformer Optimization using Adaptive and Simple Transformations
Irene Cannistraci, Simone Antonelli, Emanuele Palumbo +4
Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Exist…
Latent Space Translation via Inverse Relative Projection
Valentino Maiorca, Luca Moschella, Marco Fumero +2
The emergence of similar representations between independently trained neural models has sparked significant interest in the representation learning community, leading to the devel…
Latent Functional Maps: a spectral framework for representation alignment
Marco Fumero, Marco Pegoraro, Valentino Maiorca +2
Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these representational spaces is an ongoing challenge. By integrat…
: Cycle-Consistent Multi-Model Merging
Donato Crisostomi, Marco Fumero, Daniele Baieri +2
In this paper, we present a novel data-free method for merging neural networks in weight space. Differently from most existing works, our method optimizes for the permutations of n…
R3L: Relative Representations for Reinforcement Learning
Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella +2
Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. It is known that variations in input domains (e.g., d…