Tailai Song

Ph.D. candidate in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 38^th cycle (2022-2025)
Department of Electronics and Telecommunications (DET)

External Collaborator
Department of Electronics and Telecommunications (DET)

tailai.song@polito.it

Profile

PhD

Thesis title

From Coarse Single Theoretical to Fine Multiple Practical: Machine Learning-Empowered Real-Time Communications

Research topic

Machine learning for real-time communication.

Tutors

Keywords

Big Data, Machine Learning, Neural Networks and Data Science

Communication and Computer Networks

Modeling, simulation and CAD

Biography

I obtained the B.Sc. in Automotive Engineering at Politecnico di Torino in 2020 and the M.Sc. in ICT for Smart Societies at Politecnico di Torino in 2022. Currently, I'm a PhD student at Politecnico di Torino (PoliTO), Italy, and a member of Telecommunication Networks Group (TNG) as well as the SmartData@Polito research center. My research focuses on machine learning techniques applied to real-time communication to improve Quality of Experience (QoE).

Awards and Honors

The Best Student Paper Award in IEEE 26th International Symposium on Multimedia (ISM) 2024 (2024)

Teaching

Teachings

Master of Science

Machine learning for networking. A.A. 2024/25, CYBERSECURITY. Collaboratore del corso
Machine learning for networking. A.A. 2023/24, COMMUNICATIONS ENGINEERING. Collaboratore del corso

MostraNascondi A.A. passati

Publications

Latest publications View all publications in Porto@Iris

Song, Tailai; Garza, Paolo; Meo, Michela; Matteo Munafo, Maurizio (2026)
One Is Enough: Efficient Modeling of RTP Traffic for QoS Predictions in Real-Time Communications. In: IEEE TRANSACTIONS ON NETWORKING, vol. 34, pp. 2589-2604. ISSN 2998-4157
Contributo su Rivista
Song, Tailai; Organokov, Mukharbek; Gulikers, Lennart; Grassi, Giulio; Carofiglio, ... (2025)
Advancing Cloud-Native Cyber Threat Detection with Graph-Based Feature Engineering. In: IEEE International Conference on Data Engineering, Hong Kong (Chi), 19-23 May 2025, pp. 4291-4297. ISBN: 979-8-3315-3603-9
Contributo in Atti di Convegno (Proceeding)
Song, Tailai; Meo, Michela (2025)
Debunking Reinforcement Learning for Bandwidth Estimation in Real-Time Communications: When a Simple Regressor Suffices. In: 2025 21st International Conference on Network and Service Management (CNSM), Bologna (Ita), 27-31 October 2025
Contributo in Atti di Convegno (Proceeding)
Song, Tailai; Perna, Gianluca; Garza, Paolo; Meo, Michela; Munafo, Maurizio Matteo (2025)
Packet Loss in Real-Time Communications: Can ML Tame its Unpredictable Nature?. In: IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, vol. 22, pp. 72-91. ISSN 1932-4537
Contributo su Rivista
Song, Tailai; Garza, Paolo; Meo, Michela; Munafo, Maurizio Matteo (2024)
Modelling Concurrent RTP Flows for End-to-end Predictions of QoS in Real Time Communications. In: 26th International Symposium on Multimedia, Tokyo (JP), 11-13 December 2024, pp. 63-70. ISBN: 979-8-3315-1111-1
Contributo in Atti di Convegno (Proceeding)