Umberto Michieli

94 papers A* 6A 10B 3Misc 4Journal 61Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Clustering-driven Memory Compression for On-device Large Language Models. CoRR Ondrej Bohdal, Pramit Saha, Umberto Michieli, Mete Ozay, Taha Ceritli
2026	J	`jnl`	Data-driven Clustering and Merging of Adapters for On-device Large Language Models. CoRR Ondrej Bohdal, Taha Ceritli, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
2026	J	`jnl`	Feature-Space Generative Models for One-Shot Class-Incremental Learning. CoRR Jack Foster, Kirill Paramonov, Mete Ozay, Umberto Michieli
2026	J	`jnl`	RECALL+: Adversarial web-based replay for continual learning in semantic segmentation. Image Vis. Comput. Chang Liu, Giulia Rizzoli, Francesco Barbato, Andrea Maracani, Marco Toldo, Umberto Michieli, Yi Niu, Pietro Zanuttigh
2025	J	`jnl`	Brain-inspired sparse training enables Transformers and LLMs to perform as fully connected. CoRR Yingtao Zhang, Jialin Zhao, Wenjing Wu, Ziheng Liao, Umberto Michieli, Carlo Vittorio Cannistraci
2025	J	`jnl`	CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models. CoRR Peyman Hosseini, Ondrej Bohdal, Taha Ceritli, Ignacio Castro, Matthew Purver, Mete Ozay, Umberto Michieli
2025	A	`conf`	Continual Error Correction on Low-Resource Devices. MMSys 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
2025	J	`jnl`	Continual Error Correction on Low-Resource Devices. CoRR Kirill Paramonov, Mete Ozay, Aristeidis Mystakidis, Nikolaos Tsalikidis, Dimitrios Sotos, Anastasios Drosou, Dimitrios Tzovaras, Hyunjun Kim, Kiseok Chang, Sangdok Mo, Namwoong Kim, Woojong Yoo, Jijoong Moon, Umberto Michieli
2025	Misc	`conf`	Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning. ICASSP Kirill Paramonov, Mete Ozay, Eunju Yang, Jijoong Moon, Umberto Michieli
2025	J	`jnl`	Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning. CoRR Kirill Paramonov, Mete Ozay, Eunju Yang, Jijoong Moon, Umberto Michieli
2025	A*	`conf`	DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching. CVPR Emanuele Aiello, Umberto Michieli, Diego Valsesia, Mete Ozay, Enrico Magli
2025	A*	`conf`	Efficient Compositional Multi-tasking for On-device Large Language Models. EMNLP Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
2025	J	`jnl`	Efficient Compositional Multi-tasking for On-device Large Language Models. CoRR Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
2025	J	`jnl`	FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models. CoRR Matteo Caligiuri, Francesco Barbato, Donald Shenaj, Umberto Michieli, Pietro Zanuttigh
2025	A*	`conf`	HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging. EMNLP Taha Ceritli, Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
2025	J	`jnl`	HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging. CoRR Taha Ceritli, Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
2025	J	`jnl`	K-Merge: Online Continual Merging of Adapters for On-device Large Language Models. CoRR Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
2025	J	`jnl`	Learning From Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation. IEEE Trans. Multim. Elena Camuffo, Umberto Michieli, Simone Milani
2025	J	`jnl`	MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment. CoRR Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli
2025	J	`jnl`	MemLoRA: Distilling Expert Adapters for On-Device Memory Systems. CoRR Massimo Bini, Ondrej Bohdal, Umberto Michieli, Zeynep Akata, Mete Ozay, Taha Ceritli
2025	—	`conf`	On-device System of Compositional Multi-tasking in Large Language Models. EMNLP (Industry Track) 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	J	`jnl`	On-device System of Compositional Multi-tasking in Large Language Models. CoRR Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitris Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyeng-Hun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay, Umberto Michieli
2024	A	`conf`	A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation. MMSys Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel, Pietro Zanuttigh, Mete Ozay
2024	J	`jnl`	A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation. CoRR Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel, Pietro Zanuttigh, Mete Ozay
2024	A	`conf`	Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection. IROS Francesco Barbato, Umberto Michieli, Jijoong Moon, Pietro Zanuttigh, Mete Ozay
2024	J	`jnl`	Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection. CoRR Francesco Barbato, Umberto Michieli, Jijoong Moon, Pietro Zanuttigh, Mete Ozay
2024	J	`jnl`	Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains. CoRR Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay
2024	Misc	`conf`	Deep Neural Network Models Trained with a Fixed Random Classifier Transfer Better Across Domains. ICASSP Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay
2024	J	`jnl`	DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching. CoRR Emanuele Aiello, Umberto Michieli, Diego Valsesia, Mete Ozay, Enrico Magli
2024	A	`conf`	Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics. IROS Elena Camuffo, Umberto Michieli, Simone Milani, Jijoong Moon, Mete Ozay
2024	J	`jnl`	Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics. CoRR Elena Camuffo, Umberto Michieli, Simone Milani, Jijoong Moon, Mete Ozay
2024	Misc	`conf`	FFT-Based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images. ICASSP Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay
2024	J	`jnl`	FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images. CoRR Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay
2024	A*	`conf`	HOP to the Next Tasks and Domains for Continual Learning in NLP. AAAI Umberto Michieli, Mete Ozay
2024	J	`jnl`	HOP to the Next Tasks and Domains for Continual Learning in NLP. CoRR Umberto Michieli, Mete Ozay
2024	J	`jnl`	Learning With Style: Continual Semantic Segmentation Across Tasks and Domains. IEEE Trans. Pattern Anal. Mach. Intell. Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2024	J	`jnl`	LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation. CoRR Donald Shenaj, Ondrej Bohdal, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
2024	—	`conf`	Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. EMNLP (Findings) Hasan Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay
2024	J	`jnl`	Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. CoRR Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay
2024	Misc	`conf`	Object-Conditioned Bag of Instances for Few-Shot Personalized Instance Recognition. ICASSP Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay
2024	J	`jnl`	Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition. CoRR Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay
2024	J	`jnl`	Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation. CoRR Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik
2024	J	`jnl`	Road scenes segmentation across different domains by disentangling latent representations. Vis. Comput. Francesco Barbato, Umberto Michieli, Marco Toldo, Pietro Zanuttigh
2024	A	`conf`	Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search. IROS Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli, Jijoong Moon, Mete Ozay
2024	J	`jnl`	Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search. CoRR Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli, Jijoong Moon, Mete Ozay
2023	A	`conf`	A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization. INTERSPEECH Edward Fish, Umberto Michieli, Mete Ozay
2023	J	`jnl`	A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization. CoRR Edward Fish, Umberto Michieli, Mete Özay
2023	—	`conf`	Data-Free Model Pruning at Initialization via Expanders. CVPR Workshops James Stewart, Umberto Michieli, Mete Ozay
2023	J	`jnl`	Federated Learning via Attentive Margin of Semantic Feature Representations. IEEE Internet Things J. Umberto Michieli, Marco Toldo, Mete Ozay
2023	B	`conf`	Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation. ICIP D. Campagnolo, Elena Camuffo, Umberto Michieli, Paolo Borin, Simone Milani, Andrea Giordano
2023	A	`conf`	Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. WACV Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo
2023	J	`jnl`	Learning from Mistakes: Self-Regularizing Hierarchical Semantic Representations in Point Cloud Segmentation. CoRR Elena Camuffo, Umberto Michieli, Simone Milani
2023	A	`conf`	Online Continual Learning for Robust Indoor Object Recognition. IROS Umberto Michieli, Mete Ozay
2023	J	`jnl`	Online Continual Learning for Robust Indoor Object Recognition. CoRR Umberto Michieli, Mete Özay
2023	A	`conf`	Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics. INTERSPEECH Umberto Michieli, Pablo Peso Parada, Mete Ozay
2023	J	`jnl`	Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics. CoRR Umberto Michieli, Pablo Peso Parada, Mete Ozay
2023	J	`jnl`	RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation. CoRR Chang Liu, Giulia Rizzoli, Francesco Barbato, Umberto Michieli, Yi Niu, Pietro Zanuttigh
2023	J	`jnl`	SELMA: SEmantic Large-Scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints. IEEE Trans. Intell. Transp. Syst. Paolo Testolina, Francesco Barbato, Umberto Michieli, Marco Giordani, Pietro Zanuttigh, Michele Zorzi
2022	J	`jnl`	Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation. CoRR Donald Shenaj, Francesco Barbato, Umberto Michieli, Pietro Zanuttigh
2022	J	`jnl`	Continual coarse-to-fine domain adaptation in semantic segmentation. Image Vis. Comput. Donald Shenaj, Francesco Barbato, Umberto Michieli, Pietro Zanuttigh
2022	J	`jnl`	Edge-Aware Graph Matching Network for Part-Based Semantic Segmentation. Int. J. Comput. Vis. Umberto Michieli, Pietro Zanuttigh
2022	J	`jnl`	Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. CoRR Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo
2022	J	`jnl`	Learning with Style: Continual Semantic Segmentation Across Tasks and Domains. CoRR Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2022	J	`jnl`	SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints. CoRR Paolo Testolina, Francesco Barbato, Umberto Michieli, Marco Giordani, Pietro Zanuttigh, Michele Zorzi
2021	J	`jnl`	Adapting Segmentation Networks to New Domains by Disentangling Latent Representations. CoRR Francesco Barbato, Umberto Michieli, Marco Toldo, Pietro Zanuttigh
2021	—	`conf`	Are All Users Treated Fairly in Federated Learning Systems? CVPR Workshops Umberto Michieli, Mete Ozay
2021	A*	`conf`	Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations. CVPR Umberto Michieli, Pietro Zanuttigh
2021	J	`jnl`	Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations. CoRR Umberto Michieli, Pietro Zanuttigh
2021	J	`jnl`	Knowledge distillation for incremental learning in semantic segmentation. Comput. Vis. Image Underst. Umberto Michieli, Pietro Zanuttigh
2021	—	`conf`	Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation. CVPR Workshops Francesco Barbato, Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2021	J	`jnl`	Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation. CoRR Francesco Barbato, Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2021	J	`jnl`	Prototype Guided Federated Learning of Visual Feature Representations. CoRR Umberto Michieli, Mete Ozay
2021	A*	`conf`	RECALL: Replay-based Continual Learning in Semantic Segmentation. ICCV Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh
2021	J	`jnl`	RECALL: Replay-based Continual Learning in Semantic Segmentation. CoRR Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh
2021	A	`conf`	Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings. WACV Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2020	J	`jnl`	Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation. IEEE Trans. Intell. Veh. Umberto Michieli, Matteo Biasetton, Gianluca Agresti, Pietro Zanuttigh
2020	—	`conf`	GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild. ECCV (8) Umberto Michieli, Edoardo Borsato, Luca Rossi, Pietro Zanuttigh
2020	J	`jnl`	GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild. CoRR Umberto Michieli, Edoardo Borsato, Luca Rossi, Pietro Zanuttigh
2020	J	`jnl`	Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment. CoRR Marco Toldo, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh
2020	J	`jnl`	Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings. CoRR Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2020	J	`jnl`	Unsupervised Domain Adaptation in Semantic Segmentation: a Review. CoRR Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
2020	B	`conf`	Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training. ICPR Teo Spadotto, Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2020	J	`jnl`	Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training. CoRR Teo Spadotto, Marco Toldo, Umberto Michieli, Pietro Zanuttigh
2020	J	`jnl`	Unsupervised domain adaptation for mobile semantic segmentation based on cycle consistency and feature alignment. Image Vis. Comput. Marco Toldo, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh
2019	J	`jnl`	Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation. CoRR Umberto Michieli, Matteo Biasetton, Gianluca Agresti, Pietro Zanuttigh
2019	—	`conf`	Incremental Learning Techniques for Semantic Segmentation. ICCV Workshops Umberto Michieli, Pietro Zanuttigh
2019	J	`jnl`	Incremental Learning Techniques for Semantic Segmentation. CoRR Umberto Michieli, Pietro Zanuttigh
2019	J	`jnl`	Knowledge Distillation for Incremental Learning in Semantic Segmentation. CoRR Umberto Michieli, Pietro Zanuttigh
2019	—	`conf`	Region Merging Driven by Deep Learning for RGB-D Segmentation and Labeling. ICDSC Umberto Michieli, Maria Camporese, Andrea Agiollo, Giampaolo Pagnutti, Pietro Zanuttigh
2019	—	`conf`	Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes. CVPR Workshops Matteo Biasetton, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh
2019	—	`conf`	Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes. CVPR Workshops Matteo Biasetton, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh
2018	J	`jnl`	Complex Network Analysis of Men Single ATP Tennis Matches. CoRR Umberto Michieli
2018	B	`conf`	Game Theoretic Analysis of Road User Safety Scenarios Involving Autonomous Vehicles. PIMRC Umberto Michieli, Leonardo Badia
2018	J	`jnl`	Game Theoretic Analysis of Road User Safety Scenarios Involving Autonomous Vehicles. CoRR Umberto Michieli, Leonardo Badia