202 citations · 573 across the 58 of their papers we have counts for
66 papers
GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
Niccolò Niccoli, Silvia Dani, Marco Mistretta +3
World-level image geolocalization is an increasingly important task, yet the biases of current models remain poorly understood. Prior work has identified coarse dataset imbalances…
What DNA Foundation Models Learn Beyond Sequence Composition
Vincenzo Yuto Civale, Andrew David Bagdanov, Alberto Magi
Do genomic foundation models (FMs) provide predictive information beyond simple sequence composition? We evaluate frozen representations from five DNA FMs against normalized k-mer…
WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI-Ultrasound Learning
Francesco Correnti, Gabriele Magrini, Marco Mistretta +6
Magnetic Resonance Imaging (MRI) is widely regarded as the optimal sensor for fetal brain analysis due to its superior soft-tissue contrast and anatomical detail. However, its high…
FLaRA: Predicting Future Latent Representations for Accident Anticipation
Lorenzo Caselli, Tomaso Trinci, Tommaso Bianconcini +4
Anticipating traffic accidents from dashcam videos is a critical challenge in intelligent transportation systems. Existing methods typically map visual context directly to a collis…
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
Carlo Romeo, Andrew D. Bagdanov
Reinforcement learning for legged locomotion has matured into a stack of multi-component reward functions and physics-engine benchmarks whose morphologies are uniformly derived fro…
SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1
Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage t…
Intermediate Layers Encode Optimal Biological Representations in Single-Cell Foundation Models
Vincenzo Yuto Civale, Roberto Semeraro, Andrew David Bagdanov +1
Current single-cell foundation model benchmarks universally extract final layer embeddings, assuming these represent optimal feature spaces. We systematically evaluate layer-wise r…
Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
Giacomo Cignoni, Simone Magistri, Andrew D. Bagdanov +1
This paper explores Online Continual Self-Supervised Learning (OCSSL), a scenario in which models learn from continuous streams of unlabeled, non-stationary data, where methods typ…
Project and Mix: Task-Semantic Prototypes for Few-Shot Image Classification
Dipam Goswami, Simone Magistri, Gido M. van de Ven +4
Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that exploiting few-shot image embedd…
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
Simone Magistri, Dipam Goswami, Marco Mistretta +3
Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applie…
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…
SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
Lorenzo Caselli, Marco Mistretta, Simone Magistri +1
Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes. Training a parametric classifier…
Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion
Samuele Dell'Erba, Andrew D. Bagdanov
Diffusion models have established the state-of-the-art in text-to-image generation, but their performance often relies on a diffusion prior network to translate text embeddings int…
No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts
Girolamo Macaluso, Lorenzo Mandelli, Mirko Bicchierai +2
Diffusion models have recently advanced human motion generation, producing realistic and diverse animations from textual prompts. However, adapting these models to unseen actions o…
Accurate and Efficient Low-Rank Model Merging in Core Space
Aniello Panariello, Daniel Marczak, Simone Magistri +5
In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as…
NTRL: Encounter Generation via Reinforcement Learning for Dynamic Difficulty Adjustment in Dungeons and Dragons
Carlo Romeo, Andrew D. Bagdanov
Balancing combat encounters in Dungeons & Dragons (D&D) is a complex task that requires Dungeon Masters (DM) to manually assess party strength, enemy composition, and dynamic playe…
TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning
Alessandro Sestini, Joakim Bergdahl, Konrad Tollmar +2
In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled…
EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais +2
Exemplar-free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold…
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
Marco Mistretta, Alberto Baldrati, Lorenzo Agnolucci +2
Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individuall…
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
Daniel Marczak, Simone Magistri, Sebastian Cygert +3
Model merging integrates the weights of multiple task-specific models into a single multi-task model. Despite recent interest in the problem, a significant performance gap between…
SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1
High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability. We propose…
Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
Dipam Goswami, Simone Magistri, Kai Wang +3
Using pre-trained models has been found to reduce the effect of data heterogeneity and speed up federated learning algorithms. Recent works have explored training-free methods usin…
RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification
Marco Mistretta, Andrew D. Bagdanov
In this paper we introduce RE-tune, a novel approach for fine-tuning pre-trained Multimodal Biomedical Vision-Language models (VLMs) in Incremental Learning scenarios for multi-lab…
How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models
Tomaso Trinci, Simone Magistri, Roberto Verdecchia +1
With the ever-growing adoption of AI, its impact on the environment is no longer negligible. Despite the potential that continual learning could have towards Green AI, its environm…