Politecnico di Torino logo
Staff

Alessandro Emmanuel Pecora

Alessandro Emmanuel Pecora's picture

Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 40th cycle (2024-2027)
Department of Control and Computer Engineering (DAUIN)

Adjunct lecturer/Adjunct instructor
Department of Control and Computer Engineering (DAUIN)

Profile

PhD

Research topic

Cognitive Architectures for Agentic and Virtual Embodied AI

Tutors

Keywords

Computer graphics and Multimedia
Controls and system engineering
Data science, Computer vision and AI
Software engineering and Mobile computing

Biography

I graduated from Politecnico di Torino, where I earned my Laurea Magistrale in Data Science and Engineering in 2022. After completing my studies, I worked for one year as a Data Scientist consultant, applying advanced analytics, machine learning, and artificial intelligence techniques to complex business problems. I then spent one year as a research fellow in artificial intelligence, with a particular focus on computer vision.
I am currently part of the Computer Graphics & Vision Group (CG&VG) at Politecnico di Torino, under the supervision of Prof. Andrea Bottino and Dr. Francesco Strada. My research focuses on the development of cognitive architectures for Agentic and Virtual Embodied AI, with attention to LLMs, VLMs, virtual humans, human-computer interaction, and process automation through AI workflows.
My work investigates how intelligent agents based on Large Language Models (LLMs) and Vision-Language Models (VLMs) can integrate memory, perception, reasoning, and action to support contextual and task-oriented behaviours. The research considers a continuum of systems ranging from non-embodied agents to embodied agents, virtual humans, and intelligent avatars in virtual and XR environments.
Within this framework, learning, education, and training represent particularly relevant application domains, where agents and virtual humans can support more personalized, interactive, and engaging experiences. At the same time, the project also extends to other human-centred domains, including healthcare, simulation, decision support, and the automation of complex tasks.
A further aspect of my research concerns the study and optimization of the LLM/VLM models underlying these systems, including adaptation and fine-tuning techniques. The goal is to improve accuracy, latency, efficiency, and model specialization, making these models more suitable for implementing specific cognitive functions within complex agentic architectures.
The work is multidisciplinary and combines contributions from AI, computer vision, XR, human-computer interaction, education, game design, and psychology. In particular, psychology provides an important theoretical reference for the study of cognitive processes, memory, interaction, and behavioural models that can inspire the design of artificial cognitive architectures.

Teaching

Teachings

Bachelor of Science

Research

Research Areas/Fields/Groups

Publications

Latest publications View all publications in Porto@Iris