9 citations · 11 across the 4 of their papers we have counts for
6 papers
Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights
Irene Tallini, Daniele Solombrino, Alberto Cazzaniga +1
We show that neural network weights can be explicilty fintuned to admit a smaller grammar. Weight Pair Encoding (WeightPE) does so by placing a lossy Re-Pair compressor inside a st…
LocUS: Head Selection and Subspace Projection for Targeted Activation Steering
Irene Tallini, Lorenzo Basile, Valentino Maiorca +2
Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate a per-layer steering directi…
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…
Vector Quantile Regression on Manifolds
Marco Pegoraro, Sanketh Vedula, Aviv A. Rosenberg +3
Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given explanatory features. QR is limited by the assum…
Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
Giorgio Mariani, Irene Tallini, Emilian Postolache +3
In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources s…
Correspondence-Free Region Localization for Partial Shape Similarity via Hamiltonian Spectrum Alignment
Arianna Rampini, Irene Tallini, Maks Ovsjanikov +2
We consider the problem of localizing relevant subsets of non-rigid geometric shapes given only a partial 3D query as the input. Such problems arise in several challenging tasks in…