activity
20242026
most citedThe Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models

1 citations · 1 across the 6 of their papers we have counts for

collaborators

11 papers

cs.CV2026

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models

Quentin Guimard, Federico Bartsch, Simone Caldarella +3

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biase…

cs.CV2026

Large Multimodal Models as General In-Context Classifiers

Marco Garosi, Matteo Farina, Alessandro Conti +2

Which multimodal model should we use for classification? Previous studies suggest that the answer lies in CLIP-like contrastive Vision-Language Models (VLMs), due to their remarkab…

cs.LG2026

Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization

Davide Berasi, Matteo Farina, Massimiliano Mancini +1

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across…

cs.CV2025

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

Quentin Guimard, Moreno D'Incà, Massimiliano Mancini +1

A person downloading a pre-trained model from the web should be aware of its biases. Existing approaches for bias identification rely on datasets containing labels for the task of…

cs.CV2025

Compositional Caching for Training-free Open-vocabulary Attribute Detection

Marco Garosi, Alessandro Conti, Gaowen Liu +2

Attribute detection is crucial for many computer vision tasks, as it enables systems to describe properties such as color, texture, and material. Current approaches often rely on l…

cs.CV2025

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

Davide Berasi, Matteo Farina, Massimiliano Mancini +2

Vision-Language Models (VLMs) learn a shared feature space for text and images, enabling the comparison of inputs of different modalities. While prior works demonstrated that VLMs…