16 citations · 24 across the 9 of their papers we have counts for
9 papers
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…
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…
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-…
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…
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…
Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernels
Gonzalo Uribarri, Federico Barone, Alessio Ansuini +1
Time Series Classification (TSC) is essential in fields like medicine, environmental science, and finance, enabling tasks such as disease diagnosis, anomaly detection, and stock pr…
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…
The geometry of hidden representations of large transformer models
Lucrezia Valeriani, Diego Doimo, Francesca Cuturello +3
Large transformers are powerful architectures used for self-supervised data analysis across various data types, including protein sequences, images, and text. In these models, the…
Hierarchical nucleation in deep neural networks
Diego Doimo, Aldo Glielmo, Alessio Ansuini +1
Deep convolutional networks (DCNs) learn meaningful representations where data that share the same abstract characteristics are positioned closer and closer. Understanding these re…