activity
20242026
collaborators

7 papers

cs.CV2026

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-…

cs.LG2025

Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization

Michele Alessi, Alessio Ansuini, Alex Rodriguez

We introduce Density-Informed VAE (DiVAE), a lightweight, data-driven regularizer that aligns the VAE log-prior probability with a log-density estimated from data. St…

cs.CL2025

Persistent Topological Features in Large Language Models

Yuri Gardinazzi, Karthik Viswanathan, Giada Panerai +3

Understanding the decision-making processes of large language models is critical given their widespread applications. To achieve this, we aim to connect a formal mathematical frame…

cs.NE2025

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…

cs.LG2025

Interpreting and Steering Protein Language Models through Sparse Autoencoders

Edith Natalia Villegas Garcia, Alessio Ansuini

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a sig…

cs.CL2024

The representation landscape of few-shot learning and fine-tuning in large language models

Diego Doimo, Alessandro Serra, Alessio Ansuini +1

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite…