The SmartData@PoliTO center focuses on Big Data technologies, Data Science and Machine Learning approaches. We blend interdisciplinary people and competences from different domains to provide cross-domain solutions to the widest spectrum of knowledge discovery challenges, by leveraging advanced expertise in data science, from data management, to data modeling, analytics, and engineering. We are a well-recognized center where experts in methodologies and domain experts from various disciplines work in a single space, facing both theoretical problems and helping companies toward applications.
Presenter: Tailai SongMonday, May 6th, 2024 5:00 PMLocation: Sala Riunioni 1 DAUIN, PoliTo ABSTRACT In recent years, the modelling of Real-time Transport Protocol (RTP)-based real-time communications (RTC) applications, e.g., video-teleconferencing, has emerged as a pivotal endeavour. The potent Transformer model could be of use on the finest granularity. However, the vanilla Transformer is limited to […]
Presenter: Andrea AvignoneMonday, April 22nd, 2024 5:00 PMLocation: Sala Grande Polito@Covivio, Corso Ferrucci 112 ABSTRACT The advent of autonomous vehicles stands as a key aspect in the mobility landscape of future smart cities. This evolution requires careful considerations on matters of road safety and seamless integration within mixed traffic environments. A major area of impact […]
Presenter: Luca GioacchiniMonday, April 8th, 2024 5:00 PMLocation: Sala Grande Polito@Covivio, Corso Ferrucci 112 ABSTRACT The advances made by Large Language Models (LLMs) have led to the pursuit of Generative Agents. These are software systems that leverage foundation models like LLMs to perform complex tasks, take decisions, devise multi-steps plans and use tools (API calls, […]
Presenter: Alkis KoudounasMonday, March 11th, 2024 5:00 PMLocation: Sala Piccola Covivio, Corso Ferrucci 112 ABSTRACT Enhancing end-to-end spoken language understanding (E2E SLU) models performance, particularly for voice assistants, poses challenges in interpretability and transparency. Our research, in collaboration with Amazon Alexa AI, investigates the performance of E2E SLU models. We utilize advanced model-agnostic techniques to identify […]
