5 papers · 1 filter
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini +2
Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning effectiveness in multimodal lar…
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Matteo Farina, Vishaal Udandarao, Thao Nguyen +34
Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curat…
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
Thomas De Min, Subhankar Roy, Stéphane Lathuilière +2
Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can…
Unlearning Personal Data from a Single Image
Thomas De Min, Massimiliano Mancini, Stéphane Lathuilière +2
Machine unlearning aims to erase data from a model as if the latter never saw them during training. While existing approaches unlearn information from complete or partial access to…
Conditioned Prompt-Optimization for Continual Deepfake Detection
Francesco Laiti, Benedetta Liberatori, Thomas De Min +1
The rapid advancement of generative models has significantly enhanced the realism and customization of digital content creation. The increasing power of these tools, coupled with t…