Matteo Marchi

According to our database, Matteo Marchi authored at least 11 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Observability of Latent States in Generative AI Models.

Tian Yu Liu, Stefano Soatto, Matteo Marchi, Pratik Chaudhari, Paulo Tabuada

Proceedings of the International Conference on Neuro-symbolic Systems, 2025

Time-varying Distributed Optimization with Derivative Estimation.

João Pedro Silvestre, Matteo Marchi, Paulo Tabuada

Proceedings of the 64th IEEE Conference on Decision and Control, 2025

Boiling Frogs: Generative Models, Synthetic Data, and the Opinions of their Users.

Matteo Marchi, João Pedro Silvestre, Stefano Soatto, Pratik Chaudhari, Paulo Tabuada

Proceedings of the 64th IEEE Conference on Decision and Control, 2025

2024

Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI.

Tian Yu Liu, Stefano Soatto, Matteo Marchi, Pratik Chaudhari, Paulo Tabuada

CoRR, 2024

A Framework for Time-Varying Optimization via Derivative Estimation.

Matteo Marchi, Jonathan Bunton, João Pedro Silvestre, Paulo Tabuada

Proceedings of the European Control Conference, 2024

Heat Death of Generative Models in Closed-Loop Learning.

Matteo Marchi, Stefano Soatto, Pratik Chaudhari, Paulo Tabuada

Proceedings of the 63rd IEEE Conference on Decision and Control, 2024

2023

Sharp Performance Bounds for PASTA.

Matteo Marchi, Jonathan Bunton, Yskandar Gas, Bahman Gharesifard, Paulo Tabuada

IEEE Control. Syst. Lett., 2023

2022

Safety and Stability Guarantees for Control Loops With Deep Learning Perception.

Matteo Marchi, Jonathan Bunton, Bahman Gharesifard, Paulo Tabuada

IEEE Control. Syst. Lett., 2022

Dirty derivatives for output feedback stabilization.

Matteo Marchi, Lucas Fraile, Paulo Tabuada

CoRR, 2022

LiDAR Point Cloud Registration with Formal Guarantees.

Matteo Marchi, Jonathan Bunton, Bahman Gharesifard, Paulo Tabuada

Proceedings of the 61st IEEE Conference on Decision and Control, 2022

2021

Training deep residual networks for uniform approximation guarantees.

Matteo Marchi, Bahman Gharesifard, Paulo Tabuada

Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, 2021