Research Interests
Computer Vision
Supervisees
Papers (27)
2026
CVPR 2026
From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
CVPR Findings 2026
Large Multimodal Models as General In-Context Classifiers
CVPR Findings 2026
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini
WACV 2026
Safe Vision-Language Models via Unsafe Weights Manipulation
2025
ICCV 2025
On Large Multimodal Models as Open-World Image Classifiers
ICCV 2025
Training-Free Personalization via Retrieval and Reasoning on Fingerprints
ICIAP 2025
Automatic benchmarking of large multimodal models via iterative experiment programming
CVPR 2025
Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers
CVPR 2025
Highlight
Compositional Caching for Training-free Open-vocabulary Attribute Detection
CVPR 2025
Highlight
Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
WACV 2025
3D Part Segmentation via Geometric Aggregation of 2D Visual Features
WACV 2025
One vlm to keep it learning: Generation and balancing for data-free continual visual question answering
IEEE PAMI 2025
GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models
Moreno D’Incà, Elia Peruzzo, Massimiliano Mancini, Xingqian Xu, Humphrey Shi, Nicu Sebe
TMLR 2025
Group-robust Machine Unlearning
TMLR 2025
Unlearning Personal Data from a Single Image
2024
CVPR 2024
Harnessing Large Language Models for Training-free Video Anomaly Detection
CVPR 2024
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
CVPR 2024
Highlight
OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
Moreno D'Incà, Elia Peruzzo, Massimiliano Mancini, Dejia Xu, Vidit Goel, Xingqian Xu, Zhangyang Wang, Humphrey Shi, Nicu Sebe
CoLLAs 2024
Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning
NeurIPS 2024
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
2023
ICCV 2023
Image-free Classifier Injection for Zero-Shot Classification
Anders Christensen, Massimiliano Mancini, Almut Sophia Koepke, Ole Winther
ICCV 2023
Iterative Superquadric Recomposition of 3D Objects from Multiple Views
Stephan Alaniz, Massimiliano Mancini
ICCV 2023
On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
ICCV 2023
PDiscoNet: Semantically consistent part discovery for fine-grained recognition
Robert van der Klis, Stephan Alaniz, Massimiliano Mancini, Cassio Dantas, Dino Ienco, Diego Marcos
ICCV 2023
ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models
Uddeshya Upadhyay, Shyamgopal Karthik, Massimiliano Mancini
NeurIPS 2023
Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
Abhra Chaudhuri, Massimiliano Mancini, Anjan Dutta
NeurIPS 2023