Marco Ciccone

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior. BibTex

Gül Sena Altıntaş, Malikeh Ehghaghi, Brian Lester, Fengyuan Liu, Wanru Zhao, Marco Ciccone, Colin Raffel

ICML, 2026 (Oral)

FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment. BibTex

Riccardo Zaccone, Stefanos Laskaridis, Marco Ciccone, Samuel Horváth

ICML, 2026 (Spotlight)

The Appeal and Reality of Recycling LoRAs with Adaptive Merging. BibTex

Haokun Liu, Gyung Hyun Je, Marco Ciccone, Zhenlin Xu, Prasanth YSS, Colin Raffel

ICML, 2026

LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation. BibTex

Ahmadreza Jeddi, Marco Ciccone, Babak Taati

ICLR, 2026

Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models. BibTex

Filippo Rinaldi, Aniello Panariello, Giacomo Salici, Fengyuan Liu, Marco Ciccone, Angelo Porrello, Simone Calderara

ICLR, 2026

Schedule-Robust Continual Learning. BibTex

Ruohan Wang, Marco Ciccone, Massimiliano Pontil, Carlo Ciliberto

TPAMI, 2025

Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum. BibTex

Riccardo Zaccone, Sai Praneeth Karimireddy, Carlo Masone, Marco Ciccone

TMLR, 2025

Interaction-Aware Gaussian Weighting for Clustered Federated Learning. BibTex

Alessandro Licciardi, Davide Leo, Eros Fanì, Barbara Caputo, Marco Ciccone

ICML, 2025

Efficient Model Editing with Task-Localized Sparse Fine-tuning. BibTex

Leonardo Iurada, Marco Ciccone, Tatiana Tommasi

ICLR, 2025

Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning. BibTex

Debora Caldarola, Pietro Cagnasso, Barbara Caputo, Marco Ciccone

CVPR, 2025

Accelerating Heterogeneous Federated Learning with Closed-form Classifiers. BibTex

Eros Fanì, Raffaello Camoriano, Barbara Caputo, Marco Ciccone

ICML, 2024

Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning. BibTex

Leonardo Iurada, Marco Ciccone, Tatiana Tommasi

CVPR, 2024

PEM: Prototype-based Efficient MaskFormer for Image Segmentation. BibTex

Niccolò Cavagnero, Gabriele Rosi, Claudia Cuttano, Francesca Pistilli, Marco Ciccone, Giuseppe Averta, Fabio Cermelli

CVPR, 2024

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. BibTex

Donald Shenaj*, Eros Fanì*, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli†, Marco Ciccone†, Pietro Zanuttigh†, Barbara Caputo†

WACV, 2023

Transient-Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead. BibTex

Niccolò Cavagnero, Fernando Dos Santos, Marco Ciccone, Giuseppe Averta, Tatiana Tommasi, Paolo Rech

IOLTS, 2022

Improving Generalization in Federated Learning by Seeking Flat Minima. BibTex

Debora Caldarola*, Barbara Caputo, Marco Ciccone*

ECCV, 2022

FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving. BibTex

Lidia Fantauzzo*, Eros Fanì*, Debora Caldarola, Antonio Tavera, Fabio Cermelli, Marco Ciccone, Barbara Caputo

IROS, 2022

A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving. BibTex

Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

ICML, 2022 (Earlier version: NeurIPS 2021 CooperativeAI Workshop)

Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients. BibTex

Riccardo Zaccone, Andrea Rizzardi, Debora Caldarola, Marco Ciccone, Barbara Caputo

ICPR, 2022

Incremental Learning in Semantic Segmentation from Image Labels. BibTex

Fabio Cermelli*, Dario Fontanel*, Antonio Tavera*, Marco Ciccone, Barbara Caputo

CVPR, 2022

DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation. BibTex

Mirco Planamente*, Chiara Plizzari*, Marco Cannici*, Marco Ciccone, Francesco Strada, Andrea Bottino, Matteo Matteucci, Barbara Caputo

IROS + RAL, 2021

Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies. BibTex

Federico Cacciamani, Andrea Celli, Marco Ciccone, Nicola Gatti

AAMAS, 2021 (Earlier version: NeurIPS 2020 CooperativeAI Workshop)

A Differentiable Recurrent Surface for Asynchronous Event-Based Data. Appendix BibTex

Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

ECCV, 2020

Attention Mechanisms for Object Recognition with Event-Based Cameras. BibTex

Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

WACV, 2019

NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations. Appendix BibTex

Marco Ciccone*, Marco Gallieri*, Jonathan Masci, Christian Osendorfer, Faustino Gomez

NeurIPS, 2018

From Charts to Atlas: Merging Latent Spaces into One. BibTex

Donato Crisostomi, Irene Cannistraci, Luca Moschella, Pietro Barbiero, Marco Ciccone, Pietro Lio, Emanuele Rodolà

NeurReps Workshop @ NeurIPS, 2023

Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning. BibTex

Debora Caldarola, Barbara Caputo, Marco Ciccone

WiCV @ ICCV, 2023

Public Information Representation for Adversarial Team Games. BibTex

Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

CooperativeAI Workshop - NeurIPS, 2021 (Best Paper Award / Spotlight Talk)

Cluster-driven Graph Federated Learning over Multiple Domains. BibTex

Debora Caldarola, Massimiliano Mancini, Fabio Galasso, Marco Ciccone, Emanuele Rodolà, Barbara Caputo

Learning from Limited and Imperfect Data (L2ID) Workshop - CVPR, 2021

N-ROD: a Neuromorphic Dataset for Synthetic-to-Real Domain Adaptation. BibTex

Marco Cannici*, Chiara Plizzari*, Mirco Planamente*, Marco Ciccone, Andrea Bottino, Matteo Matteucci, Barbara Caputo

Workshop on Event-based Vision and Smart Cameras - CVPR, 2021

Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras. Appendix BibTex

Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

Workshop on Event-based Vision and Smart Cameras - CVPR, 2019 (Best Paper Award)

ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation. BibTex

Francesco Lattari*, Marco Ciccone*, Matteo Matteucci, Jonathan Masci, Francesco Visin

The 2018 DAVIS Challenge on Video Object Segmentation - CVPR Workshops, 2018

Multi-View Stereo with Single-View Semantic Mesh Refinement. BibTex

Andrea Romanoni, Marco Ciccone, Francesco Visin, Matteo Matteucci

3D Reconstruction Meets Semantic Workshop - ICCV, 2017

ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation. BibTex

Francesco Visin, Marco Ciccone, Adriana Romero, Kyle Kastner, Kyunghyun Cho, Yoshua Bengio, Matteo Matteucci, Aaron Courville

DeepVision Workshop - CVPR, 2016 (Best Paper Award)

On Iterative and Conditional Computation for Visual Representation Learning. BibTex

Marco Ciccone Advised by Prof.Matteo Matteucci, Jonathan Masci

Ph.D. Thesis (Computer Science and Engineering), Politecnico di Milano, 2021 (
[Ph.D Defense Slides])

Semantic Segmentation of Urban Scenes using Recurrent Deep Neural Networks. BibTex

Marco Ciccone Advised by Ph.D.Francesco Visin, Prof.Matteo Matteucci

M.Sc. Thesis (Computer Science and Engineering), Politecnico di Milano, 2016