25 citations · 43 across the 30 of their papers we have counts for
31 papers
iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains
Vincenzo Guarino, Emanuele Musumeci, Vincenzo Suriani +1
Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied tasks. For example, embodied age…
An LLM-Based Automatic Sportscast Solution for Robot Soccer Matches
Francesco Petri, Michele Brienza, Daniele Nardi +3
RoboCup has always been a scenario to develop systems that solve real-world problems. Driven by the main goal of playing against the 2050 FIFA World Cup champions, the RoboCup Socc…
Semantic Audio-driven Understanding for Dynamic Humanoid Whole Body Control
J. M. A. Marcelo, M. Brienza, E. Bugli +4
Recent advances in humanoid robotics and reinforcement learning have enabled the acquisition of highly expressive whole-body motion policies. However, most robotic performances rem…
Vision-Based Dribbling for Humanoid Soccer via Privileged Representation Learning
Flavio Maiorana, Valerio Spagnoli, Eugenio Bugli +5
Recent advances in humanoid robotics have highlighted the importance of deployable loco-manipulation skills. Dribbling a soccer ball while evading active opponents requires simulta…
Learning from Mistakes: Can LLM Self-Recover after Misalignment?
Olga E. Sorokoletova, Francesco Giarrusso, Vincenzo Suriani +1
Responsible AI initiatives place great emphasis on the safety of Large Language Model (LLM)-based systems. In particular, it has become standard practice to subject these models to…
Metaphor Is Not All Attention Needs
Olga Sorokoletova, Francesco Giarrusso, Giacomo De Luca +6
Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Although post-training aims to mak…
Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators
Lucía Güitta-López, Vincenzo Suriani, Jaime Boal +2
Deep Reinforcement Learning (DRL) is a powerful framework for solving complex sequential decision-making problems, particularly in robotic control. However, its practical deploymen…
Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
Marcantonio Bracale Syrnikov, Federico Pierucci, Marcello Galisai +6
Multi-agent LLM ensembles can converge on coordinated, socially harmful equilibria. This paper advances an experimental framework for evaluating Institutional AI, our system-level…
Institutional AI: A Governance Framework for Distributional AGI Safety
Federico Pierucci, Marcello Galisai, Marcantonio Syrnikov Bracale +6
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but m…
From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
Piercosma Bisconti, Marcello Galisai, Matteo Prandi +6
Safety mechanisms in LLMs remain vulnerable to attacks that reframe harmful requests through culturally coded structures. We introduce Adversarial Tales, a jailbreak technique that…
LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments
Sara Micol Ferraina, Michele Brienza, Francesco Argenziano +4
Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches rem…
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
Piercosma Bisconti, Matteo Prandi, Federico Pierucci +7
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weigh…
Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
Francesco Giarrusso, Olga E. Sorokoletova, Vincenzo Suriani +1
Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across lang…
Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
Abdel Hakim Drid, Vincenzo Suriani, Daniele Nardi +1
Navigating and understanding complex and unknown environments autonomously demands more than just basic perception and movement from embodied agents. Truly effective exploration re…
Multi Robot Coordination in Highly Dynamic Environments: Tackling Asymmetric Obstacles and Limited Communication
Vincenzo Suriani, Daniele Affinita, Domenico D. Bloisi +1
Coordinating a fully distributed multi-agent system (MAS) can be challenging when the communication channel has very limited capabilities in terms of sending rate and packet payloa…
Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
Matteo Prandi, Vincenzo Suriani, Federico Pierucci +3
The rapid advancement of General Purpose AI (GPAI) models necessitates robust evaluation frameworks, especially with emerging regulations like the EU AI Act and its associated Code…
Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots
Can Lin, Daniele Affinita, Marco E. P. Zimmatore +3
Robust and accurate ball detection is a critical component for autonomous humanoid soccer robots, particularly in dynamic and challenging environments such as RoboCup outdoor field…
Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning
Emanuele Musumeci, Michele Brienza, Francesco Argenziano +4
Embodied agents need to plan and act reliably in real and complex 3D environments. Classical planning (e.g., PDDL) offers structure and guarantees, but in practice it fails under n…
Real-Time Multimodal Signal Processing for HRI in RoboCup: Understanding a Human Referee
Filippo Ansalone, Flavio Maiorana, Daniele Affinita +8
Advancing human-robot communication is crucial for autonomous systems operating in dynamic environments, where accurate real-time interpretation of human signals is essential. Robo…
EMPOWER: Embodied Multi-role Open-vocabulary Planning with Online Grounding and Execution
Francesco Argenziano, Michele Brienza, Vincenzo Suriani +2
Task planning for robots in real-life settings presents significant challenges. These challenges stem from three primary issues: the difficulty in identifying grounded sequences of…
Multi-Agent Planning Using Visual Language Models
Michele Brienza, Francesco Argenziano, Vincenzo Suriani +2
Large Language Models (LLMs) and Visual Language Models (VLMs) are attracting increasing interest due to their improving performance and applications across various domains and tas…
Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming
Mulham Fawakherji, Vincenzo Suriani, Daniele Nardi +1
The use of deep learning methods for precision farming is gaining increasing interest. However, collecting training data in this application field is particularly challenging and c…
LLCoach: Generating Robot Soccer Plans using Multi-Role Large Language Models
Michele Brienza, Emanuele Musumeci, Vincenzo Suriani +4
The deployment of robots into human scenarios necessitates advanced planning strategies, particularly when we ask robots to operate in dynamic, unstructured environments. RoboCup o…
Play Everywhere: A Temporal Logic based Game Environment Independent Approach for Playing Soccer with Robots
Vincenzo Suriani, Emanuele Musumeci, Daniele Nardi +1
Robots playing soccer often rely on hard-coded behaviors that struggle to generalize when the game environment change. In this paper, we propose a temporal logic based approach tha…