3 citations · 4 across the 4 of their papers we have counts for
5 papers
PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution
Pierre-Luc St-Charles, Alessandro Palmas, Damiano Fornasiere +5
Reasoning models can remain capable of solving a task while still defaulting to cheaper but misleading shortcuts. This creates a central oversight problem: when a model gives an an…
Language models recognize dropout and Gaussian noise applied to their activations
Damiano Fornasiere, Mirko Bronzi, Spencer Kitts +3
We provide evidence that language models can detect, localize and, to a degree, verbalize the difference between a-semantic perturbations applied to their activations. More precise…
Reinforcement Learning for Decision-Level Interception Prioritization in Drone Swarm Defense
Alessandro Palmas
The growing threat of low-cost kamikaze drone swarms poses a critical challenge to modern defense systems demanding rapid and strategic decision-making to prioritize interceptions…
Deep Learning Computer Vision Algorithms for Real-time UAVs On-board Camera Image Processing
Alessandro Palmas, Pietro Andronico
This paper describes how advanced deep learning based computer vision algorithms are applied to enable real-time on-board sensor processing for small UAVs. Four use cases are consi…
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
Alessandro Palmas
The recent advances in reinforcement learning have led to effective methods able to obtain above human-level performances in very complex environments. However, once solved, these…