28 citations · 49 across the 17 of their papers we have counts for
20 papers
Emergent Structure in the Marginal Attention Space of Language Models
Valentino Maiorca, Walter Nelson, Francesco Locatello
While representation similarity across independently trained language models is well-documented, how internal mechanics such as attention behave across models remains far less char…
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…
Assessing Sample Quality in Conditional Generation under Compositional Shift
Berker Demirel, Valentino Maiorca, Marco Fumero +2
Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimenta…
HyperTransport: Amortized Conditioning of T2I Generative Models
Valentino Maiorca, Eleonora Gualdoni, Xavier Suau +3
As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can be costly, and while promptin…
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…
Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching
Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella +2
Deep Reinforcement Learning (RL) models often fail to generalize when even small changes occur in the environment's observations or task requirements. Addressing these shifts typic…
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…
Latent Space Translation via Inverse Relative Projection
Valentino Maiorca, Luca Moschella, Marco Fumero +2
The emergence of similar representations between independently trained neural models has sparked significant interest in the representation learning community, leading to the devel…
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…
Latent Functional Maps: a spectral framework for representation alignment
Marco Fumero, Marco Pegoraro, Valentino Maiorca +2
Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these representational spaces is an ongoing challenge. By integrat…
R3L: Relative Representations for Reinforcement Learning
Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella +2
Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. It is known that variations in input domains (e.g., d…
Latent Space Translation via Semantic Alignment
Valentino Maiorca, Luca Moschella, Antonio Norelli +3
While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible.…
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
Irene Cannistraci, Luca Moschella, Marco Fumero +2
It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases. From a geo…
Accelerating Transformer Inference for Translation via Parallel Decoding
Andrea Santilli, Silvio Severino, Emilian Postolache +4
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solv…
Attention-likelihood relationship in transformers
Valeria Ruscio, Valentino Maiorca, Fabrizio Silvestri
We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics. Our likelihood-guided text…
Bootstrapping Parallel Anchors for Relative Representations
Irene Cannistraci, Luca Moschella, Valentino Maiorca +3
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applicatio…
ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
Antonio Norelli, Marco Fumero, Valentino Maiorca +3
CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to train image and text encoders from scratch on a…
Sparse Vicious Attacks on Graph Neural Networks
Giovanni Trappolini, Valentino Maiorca, Silvio Severino +3
Graph Neural Networks (GNNs) have proven to be successful in several predictive modeling tasks for graph-structured data. Amongst those tasks, link prediction is one of the fundame…
Relative representations enable zero-shot latent space communication
Luca Moschella, Valentino Maiorca, Marco Fumero +3
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. Ideally, the distribution of the data points in the…
Metric Based Few-Shot Graph Classification
Donato Crisostomi, Simone Antonelli, Valentino Maiorca +3
Many modern deep-learning techniques do not work without enormous datasets. At the same time, several fields demand methods working in scarcity of data. This problem is even more c…