most citedActivation Patching for Interpretable Steering in Music Generation

2 citations · 4 across the 5 of their papers we have counts for

collaborators

10 papers

cs.LG2025

Two-Scale Latent Dynamics for Recurrent-Depth Transformers

Francesco Pappone, Donato Crisostomi, Emanuele Rodolà

Recurrent-depth transformers scale test-time compute by iterating latent computations before emitting tokens. We study the geometry of these iterates and argue for a simple, two-sc…

cs.LG2025

On Task Vectors and Gradients

Luca Zhou, Daniele Solombrino, Donato Crisostomi +4

Task arithmetic has emerged as a simple yet powerful technique for model merging, enabling the combination of multiple finetuned models into one. Despite its empirical success, a c…

cs.CV20251 cited

Implicit Inversion turns CLIP into a Decoder

Antonio D'Orazio, Maria Rosaria Briglia, Donato Crisostomi +3

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines…

cs.LG2025

Update Your Transformer to the Latest Release: Re-Basin of Task Vectors

Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli +6

Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g.,…

cs.LG2025

Mergenetic: a Simple Evolutionary Model Merging Library

Adrian Robert Minut, Tommaso Mencattini, Andrea Santilli +2

Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has made it increasingly popular thanks to its low c…

cs.SD20252 cited

Activation Patching for Interpretable Steering in Music Generation

Simone Facchiano, Giorgio Strano, Donato Crisostomi +4

Understanding how large audio models represent music, and using that understanding to steer generation, is both challenging and underexplored. Inspired by mechanistic interpretabil…