Aleksandar Fontana

According to our database, Aleksandar Fontana authored at least 5 papers between 2025 and 2026.

Collaborative distances:

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

2026

On the Hidden Objective Biases of Group-based Reinforcement Learning.

Aleksandar Fontana, Marco Simoni, Giulio Rossolini, Andrea Saracino, Paolo Mori

CoRR, January, 2026

2025

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence.

Marco Simoni, Aleksandar Fontana, Andrea Saracino, Paolo Mori

CoRR, October, 2025

GTPO: Trajectory-Based Policy Optimization in Large Language Models.

Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino

CoRR, August, 2025

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization.

Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino

CoRR, July, 2025

Unmasking Model Behavior: How LLMs Reason on Vulnerability Detection.

Aleksandar Fontana, Marco Simoni

Proceedings of the Availability, Reliability and Security, 2025