| 2026 | ACL | K-Merge: Online Continual Merging of Adapters for On-device Large Language Models. | Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli |
| 2025 | CVPR | DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching. | Emanuele Aiello, Umberto Michieli, Diego Valsesia, Mete Ozay, Enrico Magli |
| 2025 | EMNLP | Efficient Compositional Multi-tasking for On-device Large Language Models. | Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli |
| 2025 | EMNLP | On-device System of Compositional Multi-tasking in Large Language Models. | Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitrios Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyeng-Hun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay, Umberto Michieli |
| 2025 | EMNLP | HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging. | Taha Ceritli, Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli |
| 2025 | ICASSP | Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning. | Kirill Paramonov, Mete Ozay, Eunju Yang, Jijoong Moon, Umberto Michieli |
| 2025 | ICCV | LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation. | Donald Shenaj, Ondrej Bohdal, Mete Ozay, Pietro Zanuttigh, Umberto Michieli |
| 2025 | MMSys | Continual Error Correction on Low-Resource Devices. | Kirill Paramonov, Mete Ozay, Aristeidis Mystakidis, Nikolaos Tsalikidis, Dimitrios Sotos, Anastasios Drosou, Dimitrios Tzovaras, Hyunjun Kim, Kiseok Chang, Sangdok Mo, Namwoong Kim, Woojong Yoo, Ji Joong Moon, Umberto Michieli |
| 2024 | AAAI | HOP to the Next Tasks and Domains for Continual Learning in NLP. | Umberto Michieli, Mete Ozay |
| 2024 | EMNLP | Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. | Hasan Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay |
| 2024 | ICASSP | Deep Neural Network Models Trained with a Fixed Random Classifier Transfer Better Across Domains. | Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay |
| 2024 | ICASSP | FFT-Based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images. | Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay |
| 2024 | ICASSP | Object-Conditioned Bag of Instances for Few-Shot Personalized Instance Recognition. | Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay |
| 2024 | IROS | Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection. | Francesco Barbato, Umberto Michieli, Jijoong Moon, Pietro Zanuttigh, Mete Ozay |
| 2024 | IROS | Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics. | Elena Camuffo, Umberto Michieli, Simone Milani, Jijoong Moon, Mete Ozay |
| 2024 | IROS | Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search. | Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli, Jijoong Moon, Mete Ozay |
| 2024 | MMSys | A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation. | Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel, Pietro Zanuttigh, Mete Ozay |
| 2023 | CVPR | Data-Free Model Pruning at Initialization via Expanders. | James Stewart, Umberto Michieli, Mete Ozay |
| 2023 | ICIP | Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation. | D. Campagnolo, Elena Camuffo, Umberto Michieli, Paolo Borin, Simone Milani, Andrea Giordano |
| 2023 | Interspeech | A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization. | Edward Fish, Umberto Michieli, Mete Ozay |
| 2023 | Interspeech | Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics. | Umberto Michieli, Pablo Peso Parada, Mete Ozay |
| 2023 | IROS | Online Continual Learning for Robust Indoor Object Recognition. | Umberto Michieli, Mete Ozay |
| 2023 | WACV | Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. | Donald Shenaj, Eros Fan, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo |
| 2021 | CVPR | Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation. | Francesco Barbato, Marco Toldo, Umberto Michieli, Pietro Zanuttigh |
| 2021 | CVPR | Are All Users Treated Fairly in Federated Learning Systems? | Umberto Michieli, Mete Ozay |
| 2021 | CVPR | Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations. | Umberto Michieli, Pietro Zanuttigh |
| 2021 | ICCV | RECALL: Replay-based Continual Learning in Semantic Segmentation. | Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh |
| 2021 | WACV | Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings. | Marco Toldo, Umberto Michieli, Pietro Zanuttigh |
| 2020 | ECCV | GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild. | Umberto Michieli, Edoardo Borsato, Luca Rossi, Pietro Zanuttigh |
| 2020 | ICPR | Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training. | Teo Spadotto, Marco Toldo, Umberto Michieli, Pietro Zanuttigh |
| 2019 | CVPR | Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes. | Matteo Biasetton, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh |
| 2019 | CVPR | Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes. | Matteo Biasetton, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh |
| 2018 | PIMRC | Game Theoretic Analysis of Road User Safety Scenarios Involving Autonomous Vehicles. | Umberto Michieli, Leonardo Badia |