2 citations · 4 across the 7 of their papers we have counts for
10 papers
Deep learning from a control vantage point
Álvaro Rodríguez Abella, João Pedro Silvestre, Bahman Gharesifard +1
This article offers an overview of recent developments in deep learning from a control vantage point. It reviews several classes of models including feedforward and residual neural…
PESTO: Formally Correct Registration of LiDAR Point Clouds with Limited Overlap
Valen Yamamoto, Matteo Marchi, Paulo Tabuada
In this paper we tackle the problem of aligning LiDAR point clouds also known as the point cloud registration problem. We propose a new algorithm, PESTO, that exploits tetrahedra a…
The Attention Within: Consensus Dynamics in Selective State Space Models
João Pedro Silvestre, Álvaro Rodríguez Abella, Paulo Tabuada
Selective state space models (SSMs) have recently emerged as a compelling alternative to transformers, combining competitive performance with substantially improved inference effic…
Predicting Viral Evolution from a Single Early Measurement Using the Target Cell Limited Model
Rahal Nanayakkara, Paulo Tabuada
Recent advances in diagnostic techniques have enabled the accurate quantification of early-stage viral loads. A key problem of interest is translating these measurements into predi…
Safety Under State Uncertainty: Robustifying Control Barrier Functions
Rahal Nanayakkara, Aaron D. Ames, Paulo Tabuada
Safety-critical control is a crucial aspect of modern systems, and Control Barrier Functions (CBFs) have gained popularity as the framework of choice for ensuring safety. However,…
Safe Navigation under State Uncertainty: Online Adaptation for Robust Control Barrier Functions
Ersin Das, Rahal Nanayakkara, Xiao Tan +4
Measurements and state estimates are often imperfect in control practice, posing challenges for safety-critical applications, where safety guarantees rely on accurate state informa…
The Asymptotic Behavior of Attention in Transformers
Álvaro Rodríguez Abella, João Pedro Silvestre, Paulo Tabuada
The transformer architecture has become the foundation of modern Large Language Models (LLMs), yet its theoretical properties are still not well understood. As with classic neural…
Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI
Tian Yu Liu, Stefano Soatto, Matteo Marchi +2
We tackle the question of whether Large Language Models (LLMs), viewed as dynamical systems with state evolving in the embedding space of symbolic tokens, are observable. That is,…
Heat Death of Generative Models in Closed-Loop Learning
Matteo Marchi, Stefano Soatto, Pratik Chaudhari +1
Improvement and adoption of generative machine learning models is rapidly accelerating, as exemplified by the popularity of LLMs (Large Language Models) for text, and diffusion mod…
A Framework for Time-Varying Optimization via Derivative Estimation
Matteo Marchi, Jonathan Bunton, João Pedro Silvestre +1
Optimization algorithms have a rich and fundamental relationship with ordinary differential equations given by its continuous-time limit. When the cost function varies with time --…