Massimiliano Mancini

Benchmarking XAI Explanations with Human-Aligned Evaluations AAAI 2026 From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition CVPR 2026 Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026 3D Part Segmentation via Geometric Aggregation of 2D Visual Features WACV 2025 Can Text-to-Video Generation help Video-Language Alignment? CVPR 2025 Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers CVPR 2025 Compositional Caching for Training-free Open-vocabulary Attribute Detection CVPR 2025 Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models CVPR 2025 One VLM to Keep it Learning: Generation and Balancing for Data-Free Continual Visual Question Answering WACV 2025 On Large Multimodal Models as Open-World Image Classifiers ICCV 2025 Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages CVPR 2025 Training-Free Personalization via Retrieval and Reasoning on Fingerprints ICCV 2025 Frustratingly Easy Test-Time Adaptation of Vision-Language Models NeurIPS 2024 Harnessing Large Language Models for Training-free Video Anomaly Detection CVPR 2024 MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning CVPR 2024 OpenBias: Open-set Bias Detection in Text-to-Image Generative Models CVPR 2024 Vision-by-Language for Training-Free Compositional Image Retrieval ICLR 2024 Image-Free Classifier Injection for Zero-Shot Classification ICCV 2023 Iterative Superquadric Recomposition of 3D Objects from Multiple Views ICCV 2023 PDiscoNet: Semantically consistent part discovery for fine-grained recognition ICCV 2023 ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models ICCV 2023 Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships NeurIPS 2023 Vocabulary-free Image Classification NeurIPS 2023 Abstracting Sketches through Simple Primitives ECCV 2022 BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks ECCV 2022 KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning CVPR 2022 Relational Proxies: Emergent Relationships as Fine-Grained Discriminators NeurIPS 2022 Open World Compositional Zero-Shot Learning CVPR 2021 Modeling the Background for Incremental Learning in Semantic Segmentation CVPR 2020 Towards Recognizing Unseen Categories in Unseen Domains ECCV 2020 AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs CVPR 2019 Boosting Domain Adaptation by Discovering Latent Domains CVPR 2018 Embedding Words and Senses Together via Joint Knowledge-Enhanced Training CoNLL 2017