Home
News
Publications
People
NeXuS
Contact
1
Foundation Models on a Budget: Approximating Blocks in Large Vision Models
Deep neural networks often learn similar internal representations, both across different models and within their own layers. While …
Irene Cannistraci
,
Simone Antonelli
,
Emanuele Palumbo
,
Thomas M. Sutter
,
Emanuele Rodolà
,
Bastian Rieck
,
Julia E. Vogt
Cite
arXiv
LoopGen: Training-Free Loopable Music Generation
Loops–short audio segments designed for seamless repetition–are central to many music genres, particularly those rooted in …
Davide Marincione
,
Giorgio Strano
,
Donato Crisostomi
,
Roberto Ribuoli
,
Emanuele Rodolà
Cite
arXiv
STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering …
Giorgio Strano
,
Chiara Ballanti
,
Donato Crisostomi
,
Michele Mancusi
,
Luca Cosmo
,
Emanuele Rodolà
Cite
arXiv
GitHub
Mergenetic: a Simple Evolutionary Model Merging Library
Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has …
Adrian R. Minut
,
Tommaso Mencattini
,
Andrea Santilli
,
Donato Crisostomi
,
Emanuele Rodolà
Cite
arXiv
GitHub
MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs
Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for …
Tommaso Mencattini
,
Adrian R. Minut
,
Donato Crisostomi
,
Andrea Santilli
,
Emanuele Rodolà
Cite
arXiv
GitHub
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying …
Filippo Rinaldi
,
Giacomo Capitani
,
Lorenzo Bonicelli
,
Angelo Porrello
,
Donato Crisostomi
,
Federico Bolelli
,
Emanuele Rodolà
,
Elisa Ficarra
,
Simone Calderara
Cite
Model-based Metric 3D Shape and Motion Reconstruction of Wild Bottlenose Dolphins in Drone-Shot Videos
We address the problem of estimating the metric 3D shape and motion of wild dolphins from monocular video, with the aim of assessing …
Daniele Baieri
,
Riccardo Cicciarella
,
Michael Krützen
,
Emanuele Rodolà
,
Silvia Zuffi
Cite
arXiv
Task Singular Vectors: Reducing Task Interference in Model Merging
Task Arithmetic has emerged as a simple yet effective method to merge models without additional training. However, by treating entire …
Antonio Andrea Gargiulo
,
Donato Crisostomi
,
Maria Sofia Bucarelli
,
Simone Scardapane
,
Fabrizio Silvestri
,
Emanuele Rodolà
Cite
arXiv
GitHub
Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces
In this work, we investigate the possibility of a posteriori alignment of representations obtained from uni-modal 3D encoders compared …
Souhail Hadgi
,
Luca Moschella
,
Andrea Santilli
,
Diego Gomez
,
Qixing Huang
,
Emanuele Rodolà
,
Simone Melzi
,
Maks Ovsjanikov
Cite
arXiv
PDF
Naturalistic Music Decoding from EEG Data via Latent Diffusion Models
In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of …
Emilian Postolache
,
Natalia Polouliakh
,
Hiroaki Kitano
,
Akima Connelly
,
Emanuele Rodolà
,
Luca Cosmo
,
Taketo Akama
Cite
arXiv
»
Cite
×