This website uses cookies to ensure you get the best experience on our website.
Learn more
Got it!
Home
News
Publications
People
NeXuS
Contact
3
Video Unlearning via Low-Rank Refusal Vector
Video generative models democratize the creation of visual content through intuitive instruction following, but they also inherit the …
Simone Facchiano
,
Stefano Saravalle
,
Matteo Migliarini
,
Edoardo De Matteis
,
Alessio Sampieri
,
Andrea Pilzer
,
Emanuele Rodolà
,
Indro Spinelli
,
Luca Franco
,
Fabio Galasso
Cite
arXiv
GitHub
Implicit Inversion turns CLIP into a Decoder
CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves …
Antonio D'Orazio
,
Maria Rosaria Briglia
,
Donato Crisostomi
,
Dario Loi
,
Emanuele Rodolà
,
Iacopo Masi
Cite
arXiv
GitHub
Navigating the Latent Space Dynamics of Neural Models
Neural networks transform high-dimensional data into compact, structured representations, often modeled as elements of a lower …
Marco Fumero
,
Luca Moschella
,
Emanuele Rodolà
,
Francesco Locatello
Cite
arXiv
Activation Patching for Interpretable Steering in Music Generation
Understanding how large audio models represent music, and using that understanding to steer generation, is both challenging and …
Simone Facchiano
,
Giorgio Strano
,
Donato Crisostomi
,
Irene Tallini
,
Tommaso Mencattini
,
Fabio Galasso
,
Emanuele Rodolà
Cite
arXiv
MASS: MoErging through Adaptive Subspace Selection
Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set …
Donato Crisostomi
,
Alessandro Zirilli
,
Antonio Andrea Gargiulo
,
Maria Sofia Bucarelli
,
Simone Scardapane
,
Fabrizio Silvestri
,
Iacopo Masi
,
Emanuele Rodolà
Cite
arXiv
Decoding RNA-RNA Interactions: The Role of Low-Complexity Repeats and a Deep Learning Framework for Sequence-Based Prediction
RNA-RNA interactions (RRIs) are fundamental to gene regulation and RNA processing, yet their molecular determinants remain unclear. In …
Adriano Setti
,
Giorgio Bini
,
Valentino Maiorca
,
Flaminia Pellegrini
,
Gabriele Proietti
,
Dimitrios Miltiadis-Vrachnos
,
Alexandros Armaos
,
Julie Martone
,
Michele Monti
,
Giancarlo Ruocco
,
Emanuele Rodolà
,
Irene Bozzoni
,
Alessio Colantoni
,
Gian Gaetano Tartaglia
Cite
bioRxiv
GitHub
Humanity's Last Exam
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are …
More than 600 authors including
,
Donato Crisostomi
,
Emanuele Rodolà
Cite
URL
GitHub
arXiv
COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations …
Ruben Ciranni
,
Giorgio Mariani
,
Michele Mancusi
,
Emilian Postolache
,
Giorgio Fabbro
,
Emanuele Rodolà
,
Luca Cosmo
Cite
arXiv
GitHub
ATM: Improving Model Merging by Alternating Tuning and Merging
Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic …
Luca Zhou
,
Daniele Solombrino
,
Donato Crisostomi
,
Maria Sofia Bucarelli
,
Fabrizio Silvestri
,
Emanuele Rodolà
Cite
arXiv
GitHub
ResiDual Transformer Alignment with Spectral Decomposition
When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions …
Lorenzo Basile
,
Valentino Maiorca
,
Luca Bortolussi
,
Emanuele Rodolà
,
Francesco Locatello
Cite
arXiv
»
Cite
×