Publications

• J. M. Goo, X. Milidonis, A. Artusi, J. Boehm, and C. Ciliberto. Hybrid-Segmentor: Hybrid approach for automated fine-grained crack segmentation in civil infrastructure. Automation in Construction, 2025.
• S. Shanks, J. Embley-Riches, J. Liu, A. M. Delfaki, C. Ciliberto, and D. Kanoulas. DreamerNav: learning-based autonomous navigation in dynamic indoor environments using world models. Frontiers in Robotics and AI, 2025.
• R. Wang, M. Ciccone, M. Pontil, and C. Ciliberto. Schedule-Robust Continual Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.
• T. Cantelobre, C. Ciliberto, B. Guedj, and A. Rudi. Closed-form Filtering for Non-linear Systems. arXiv preprint arXiv:2402.09796, 2024.
• P. Novelli, M. Pratticò, M. Pontil, and C. Ciliberto. Operator world models for reinforcement learning. Advances in Neural Information Processing Systems, 2024.
• R. Wang, W. Fu, and C. Ciliberto. Deep Tabular Learning via Distillation and Language Guidance. Transactions on Machine Learning Research, 2024.
• C. Ciliberto, M. Pontil, and D. Stamos. Reexamining low rank matrix factorization for trace norm regularization. Mathematics in Engineering, 2023.
• R. Wang, J. I. T. Falk, M. Pontil, and C. Ciliberto. Robust meta-representation learning via global label inference and classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
• G. Denevi, M. Pontil, and C. Ciliberto. Conditional meta-learning of linear representations. Advances in Neural Information Processing Systems, 2022.
• D. Meunier, M. Pontil, and C. Ciliberto. Distribution regression with sliced Wasserstein kernels. International Conference on Machine Learning, 2022.
• T. Cantelobre, C. Ciliberto, B. Guedj, and A. Rudi. Measuring dissimilarity with diffeomorphism invariance. arXiv preprint arXiv:2202.05614, 2022.
• D. Antotsiou, C. Ciliberto, and T. Kim. Modular adaptive policy selection for multi-task imitation learning through task division. 2022 International Conference on Robotics and Automation (ICRA), 2022.
• J. I. T. Falk, C. Cilibert, and M. Pontil. Implicit kernel meta-learning using kernel integral forms. Uncertainty in Artificial Intelligence, 2022.
• V. Kostic, P. Novelli, A. Maurer, C. Ciliberto, L. Rosasco, and M. Pontil. Learning dynamical systems via Koopman operator regression in reproducing kernel Hilbert spaces. Advances in Neural Information Processing Systems, 2022.
• G. M. Marconi, R. Camoriano, L. Rosasco, and C. Ciliberto. Structured prediction for CRiSP inverse kinematics learning with misspecified robot models. IEEE Robotics and Automation Letters, 2021.
• D. Antotsiou, C. Ciliberto, and T. Kim. Adversarial imitation learning with trajectorial augmentation and correction. 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021.
• A. Rudi and C. Ciliberto. PSD representations for effective probability models. Advances in Neural Information Processing Systems, 2021.
• R. Wang, M. Pontil, and C. Ciliberto. The role of global labels in few-shot classification and how to infer them. Advances in Neural Information Processing Systems, 2021.
• A. Rudi, L. Wossnig, C. Ciliberto, A. Rocchetto, M. Pontil, and S. Severini. Approximating Hamiltonian dynamics with the Nyström method. Quantum, 2020.
• C. Ciliberto, L. Rosasco, and A. Rudi. A general framework for consistent structured prediction with implicit loss embeddings. Journal of Machine Learning Research, 2020.
• R. Wang, C. Ciliberto, P. Amadori, and Y. Demiris. Support-weighted adversarial imitation learning. arXiv preprint arXiv:2002.08803, 2020.
• G. Marconi, C. Ciliberto, and L. Rosasco. Hyperbolic manifold regression. International Conference on Artificial Intelligence and Statistics, 2020.
• G. Luise, M. Pontil, and C. Ciliberto. Generalization properties of optimal transport GANs with latent distribution learning. arXiv preprint arXiv:2007.14641, 2020.
• G. Denevi, M. Pontil, and C. Ciliberto. The advantage of conditional meta-learning for biased regularization and fine tuning. Advances in Neural Information Processing Systems, 2020.
• C. Ciliberto, A. Rocchetto, A. Rudi, and L. Wossnig. Statistical limits of supervised quantum learning. Physical Review A, 2020.
• L. Oneto, M. Donini, G. Luise, C. Ciliberto, A. Maurer, and M. Pontil. Exploiting mmd and sinkhorn divergences for fair and transferable representation learning. Advances in Neural Information Processing Systems, 2020.
• R. Wang, Y. Demiris, and C. Ciliberto. Structured prediction for conditional meta-learning. Advances in Neural Information Processing Systems, 2020.
• G. Pasquale, C. Ciliberto, F. Odone, L. Rosasco, and L. Natale. Are we done with object recognition? The iCub robot’s perspective. Robotics and Autonomous Systems, 2019.
• C. Ciliberto, F. Bach, and A. Rudi. Localized structured prediction. Advances in Neural Information Processing Systems, 2019.
• G. Luise, D. Stamos, M. Pontil, and C. Ciliberto. Leveraging low-rank relations between surrogate tasks in structured prediction. International Conference on Machine Learning, 2019.
• G. Denevi, C. Ciliberto, R. Grazzi, and M. Pontil. Learning-to-learn stochastic gradient descent with biased regularization. International Conference on Machine Learning, 2019.
• R. Wang, C. Ciliberto, P. V. Amadori, and Y. Demiris. Random expert distillation: Imitation learning via expert policy support estimation. International Conference on Machine Learning, 2019.
• G. Luise, S. Salzo, M. Pontil, and C. Ciliberto. Sinkhorn barycenters with free support via frank-wolfe algorithm. Advances in neural information processing systems, 2019.
• G. Denevi, D. Stamos, C. Ciliberto, and M. Pontil. Online-within-online meta-learning. Advances in Neural Information Processing Systems, 2019.
• C. Ciliberto, M. Herbster, A. D. Ialongo, M. Pontil, A. Rocchetto, S. Severini, and L. Wossnig. Quantum machine learning: a classical perspective. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2018.
• G. Denevi, C. Ciliberto, D. Stamos, and M. Pontil. Incremental learning-to-learn with statistical guarantees. arXiv preprint arXiv:1803.08089, 2018.
• G. Luise, A. Rudi, M. Pontil, and C. Ciliberto. Differential properties of sinkhorn approximation for learning with wasserstein distance. Advances in Neural Information Processing Systems, 2018.
• A. Rudi, C. Ciliberto, G. Marconi, and L. Rosasco. Manifold structured prediction. Advances in Neural Information Processing Systems, 2018.
• G. Denevi, C. Ciliberto, D. Stamos, and M. Pontil. Learning to learn around a common mean. Advances in neural information processing systems, 2018.
• S. R. Fanello, C. Ciliberto, N. Noceti, G. Metta, and F. Odone. Visual recognition for humanoid robots. Robotics and Autonomous Systems, 2017.
• R. Camoriano, G. Pasquale, C. Ciliberto, L. Natale, L. Rosasco, and G. Metta. Teaching robots to learn new objects in constant time. arXiv preprint arXiv:1605.05045, 2017.
• C. Ciliberto, A. Rudi, L. Rosasco, and M. Pontil. Consistent multitask learning with nonlinear output relations. Advances in Neural Information Processing Systems, 2017.
• R. Camoriano, G. Pasquale, C. Ciliberto, L. Natale, L. Rosasco, and G. Metta. Incremental robot learning of new objects with fixed update time. 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017.
• C. Ciliberto, D. Stamos, and M. Pontil. Reexamining low rank matrix factorization for trace norm regularization. arXiv preprint arXiv:1706.08934, 2017.
• S. Ryan Fanello, J. Valentin, A. Kowdle, C. Rhemann, V. Tankovich, C. Ciliberto, P. Davidson, and S. Izadi. Low compute and fully parallel computer vision with hashmatch. Proceedings of the IEEE International Conference on Computer Vision, 2017.
• C. Ciliberto. Connecting YARP to the Web with Yarp. js. Frontiers in Robotics and AI, 2017.
• G. Pasquale, T. Mar, C. Ciliberto, L. Rosasco, and L. Natale. Enabling depth-driven visual attention on the icub humanoid robot: Instructions for use and new perspectives. Frontiers in Robotics and AI, 2016.
• R. Camoriano, G. Pasquale, C. Ciliberto, L. Natale, L. Rosasco, and G. Metta. Incremental object recognition in robotics with extension to new classes in constant time. stat, 2016.
• C. Ciliberto, L. Rosasco, and A. Rudi. A consistent regularization approach for structured prediction. Advances in neural information processing systems, 2016.
• G. Pasquale, C. Ciliberto, L. Rosasco, and L. Natale. Object identification from few examples by improving the invariance of a deep convolutional neural network. 2016 IEEE/RSJ international conference on intelligent robots and systems (IROS), 2016.
• N. Jamali, C. Ciliberto, L. Rosasco, and L. Natale. Active perception: Building objects' models using tactile exploration. 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016.
• B. Higy, C. Ciliberto, L. Rosasco, and L. Natale. Combining sensory modalities and exploratory procedures to improve haptic object recognition in robotics. 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016.
• C. Ciliberto, Y. Mroueh, T. Poggio, and L. Rosasco. Convex learning of multiple tasks and their structure. International Conference on Machine Learning, 2015.
• C. Ciliberto, L. Rosasco, and S. Villa. Learning multiple visual tasks while discovering their structure. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
• G. Pasquale, C. Ciliberto, F. Odone, L. Rosasco, and L. Natale. Real-world object recognition with off-the-shelf deep conv nets: How many objects can icub learn?. arXiv preprint arXiv:1504.03154, 2015.
• G. Pasquale, C. Ciliberto, F. Odone, L. Rosasco, and L. Natale. Teaching icub to recognize objects using deep convolutional neural networks. Machine Learning for Interactive Systems, 2015.
• G. L. Breschi, C. Ciliberto, T. Nieus, L. Rosasco, S. Taverna, M. Chiappalone, and V. Pasquale. Characterizing the Input-Output Function of the Olfactory-Limbic Pathway in the Guinea Pig. Computational Intelligence and Neuroscience, 2015.
• S. Ryan Fanello, N. Noceti, C. Ciliberto, G. Metta, and F. Odone. Ask the image: supervised pooling to preserve feature locality. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014.
• C. Ciliberto, L. Fiorio, M. Maggiali, L. Natale, L. Rosasco, G. Metta, G. Sandini, and F. Nori. Exploiting global force torque measurements for local compliance estimation in tactile arrays. 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2014.
• S. R. Fanello, C. Ciliberto, L. Natale, and G. Metta. Weakly supervised strategies for natural object recognition in robotics. 2013 IEEE International Conference on Robotics and Automation, 2013.
• S. Fanello, C. Ciliberto, M. Santoro, L. Natale, G. Metta, L. Rosasco, and F. Odone. icub world: Friendly robots help building good vision data-sets. Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2013.
• C. Ciliberto, S. R. Fanello, M. Santoro, L. Natale, G. Metta, and L. Rosasco. On the impact of learning hierarchical representations for visual recognition in robotics. Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on, 2013.
• C. Ciliberto, S. R. Fanello, M. Santoro, L. Natale, G. Metta, T. Poggio, and L. Rosasco. Learning Hierarchical Representations for Visual Recognition in Robotics, 2013.
• C. Ciliberto, S. R. Fanello, L. Natale, and G. Metta. A heteroscedastic approach to independent motion detection for actuated visual sensors. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012.
• C. Ciliberto, U. Pattacini, L. Natale, F. Nori, and G. Metta. Reexamining lucas-kanade method for real-time independent motion detection: Application to the icub humanoid robot. 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011.
• C. Ciliberto, F. Smeraldi, L. Natale, and G. Metta. Online multiple instance learning applied to hand detection in a humanoid robot. 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011.