Institution profile

Sapienza University of Rome

Academic institutioneurope · it
Official website
Research library620linked papers
Opportunities0open roles
Selected work

Representative Papers

Coordinated inauthentic behavior and information spreading on Twitter

Jun 01, 2022Decision Support Systems

This work investigates how coordinated inauthentic accounts (e.g., bot clusters) on Twitter manipulate information diffusion algorithms and amplify misinformation through temporally consistent anomalous behaviors. To address the limitation of existing methods—namely, their failure to model multi-level propagation dynamics—we propose the first systematic framework for modeling coordinated misinformation behavior. Our approach integrates graph neural networks, temporal behavioral clustering, causal inference over propagation paths, and multi-source feature fusion. We design a detection model grounded in behavioral temporal consistency, achieving 89.7% accuracy in identifying coordinated inauthentic accounts on a real-world Twitter dataset. Furthermore, we uncover three novel information manipulation topologies—previously unreported—revealing positional preferences of coordinated actors within propagation chains, characteristic delay patterns, and mechanisms by which coordination amplifies influence.

32 citations3 influentialRead paper

On-Line Learning for Planning and Control of Underactuated Robots With Uncertain Dynamics

Jan 01, 2022IEEE Robotics and Automation Letters

Underactuated robots—such as the Pendubot—exhibit severe dynamic model uncertainty, hindering reliable trajectory planning and high-precision tracking. Method: This paper proposes a co-design framework integrating online learning with motion planning and control. It combines real-time disturbance estimation, optimization-based trajectory planning, and partial feedback linearization of actuated degrees of freedom to enable concurrent model adaptation and iterative controller refinement. Contribution/Results: We introduce the first “planning–control joint online learning” mechanism, achieving dynamically feasible trajectory generation and precise tracking within minimal iterations. Comprehensive simulations and hardware experiments demonstrate rapid convergence and robust performance despite large modeling errors—significantly enhancing system robustness and adaptability to unmodeled dynamics and disturbances.

7 citationsRead paper

Assembling Solar Panels by Dual Robot Arms Towards Full Autonomous Lunar Base Construction

Jan 21, 2025IEEE/SICE International Symposium on System Integration

This work proposes a fully autonomous, modular solar panel assembly system tailored for lunar environments to support future lunar base construction. Addressing challenges such as low gravity and the absence of GPS, the system integrates a dual robotic arm with cooperative control, a specialized grasping connector, and a hybrid active-passive docking mechanism. An end-to-end autonomous assembly pipeline is developed, incorporating real-time visual localization, pose estimation, and motion planning. Experiments conducted in a simulated lunar environment demonstrate successful automatic identification, alignment, and reliable connection of solar panel modules from arbitrary initial poses, confirming the system’s high robustness and engineering feasibility for complex space missions.

5 citationsRead paper

Hidden assumptions of integer ratio analyses in bioacoustics and music

Feb 06, 2025

Widely adopted integer-ratio analyses in bioacoustics and music rhythm research suffer from critical methodological flaws: inadequate modeling of temporal noise, sensitivity of statistical inference to ratio formulation choices, and longstanding neglect of null-hypothesis appropriateness. Method: We formally characterize the temporal properties of empirically observed rhythmic ratios and introduce the first general-purpose statistical testing framework for integer ratios—flexibly accommodating arbitrary null hypotheses. This framework integrates mathematical modeling, probabilistic distribution analysis, and rigorous hypothesis testing to systematically identify the sources of statistical bias in prevailing approaches. Contribution/Results: The framework rectifies long-overlooked methodological shortcomings and provides a standardized, reproducible testing protocol. It substantially enhances statistical robustness and cross-study comparability in cross-species rhythmic analyses and music cognition research, enabling principled inference about rhythmic structure beyond ad hoc ratio assessments.

3 citations1 influentialRead paper

Memorization to Generalization: Emergence of Diffusion Models from Associative Memory

May 27, 2025

This work investigates the memory–generalization phase transition in diffusion models under varying training data scales. We propose a *correlational memory* perspective: training corresponds to memory encoding, while generation implements memory retrieval. We establish, for the first time, a theoretical connection between diffusion models and Hopfield networks, deriving necessary and sufficient conditions for the emergence of *spurious attractors*—hallucinated states—at the critical memory load threshold. Leveraging energy landscape analysis, dynamical systems modeling, and empirical validation on DDPM and DDIM, we confirm the universality of this phenomenon. Results show that models operate dominantly in memory mode under small-data regimes, shift toward generalization with large-scale data, and exhibit spurious attractors in the critical regime—unifying explanations for memory overload and implicit manifold learning. This work provides a cross-disciplinary theoretical framework and falsifiable predictions for understanding the intrinsic mechanisms of diffusion models.

3 citationsRead paper
Recent publications

Latest Papers