2 citations · 3 across the 9 of their papers we have counts for
10 papers
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…
Visual Instruction Tuning Aligns Modalities through Abstraction
Luis Palacios, Lorenzo Basile, Diego Doimo +1
Visual instruction tuning effectively adapts a pre-trained Large Language Model (LLM) to process image information alongside text. Yet, it remains unclear how visual features are e…
Head Pursuit: Probing Attention Specialization in Multimodal Transformers
Lorenzo Basile, Valentino Maiorca, Diego Doimo +2
Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we st…
Harvesting energy from turbulent winds with Reinforcement Learning
Lorenzo Basile, Maria Grazia Berni, Antonio Celani
Airborne Wind Energy (AWE) is an emerging technology designed to harness the power of high-altitude winds, offering a solution to several limitations of conventional wind turbines.…
The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models
Alessandro Pietro Serra, Francesco Ortu, Emanuele Panizon +5
Recent advances in multimodal training have significantly improved the integration of image understanding and generation within a unified model. This study investigates how vision-…
ResiDual Transformer Alignment with Spectral Decomposition
Lorenzo Basile, Valentino Maiorca, Luca Bortolussi +2
When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions (e.g., attention heads) sometimes specialize i…
Scalable unsupervised alignment of general metric and non-metric structures
Sanketh Vedula, Valentino Maiorca, Lorenzo Basile +2
Aligning data from different domains is a fundamental problem in machine learning with broad applications across very different areas, most notably aligning experimental readouts i…
Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations
Lorenzo Basile, Santiago Acevedo, Luca Bortolussi +2
To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations o…
Emergent representations in networks trained with the Forward-Forward algorithm
Niccolò Tosato, Lorenzo Basile, Emanuele Ballarin +3
The Backpropagation algorithm has often been criticised for its lack of biological realism. In an attempt to find a more biologically plausible alternative, the recently introduced…
Frequency maps reveal the correlation between Adversarial Attacks and Implicit Bias
Lorenzo Basile, Nikos Karantzas, Alberto d'Onofrio +4
Despite their impressive performance in classification tasks, neural networks are known to be vulnerable to adversarial attacks, subtle perturbations of the input data designed to…