Howdy visitor, I’m Emanuele (/emanu’ɛle/), a research scientist at Google DeepMind in Grenoble 🇫🇷, working on multimodal AI. My interests lie in the intersection of machine learning, natural language processing and vision to understand and develop human-like artificial intelligence. I’m especially interested in multimodal and multilingual grounding and generation, and in probing the abilities and properties of such models.

I received my PhD from the NLP Section at the University of Copenhagen 🇩🇰, as a member of the LAMP and CoAStaL groups. During my PhD, I interned at Google Research 🇨🇭, DeepMind 🇬🇧, Mila 🇨🇦, and Spotify Research 🇬🇧. Before my PhD, I spent one year at Okazaki Laboratory 🇯🇵. I received my master’s degree from the School of Computer and Communication Sciences at EPFL 🇨🇭, where I was a member of the Data Science Lab, and two bachelor’s degrees from Tongji University 🇨🇳 and Politecnico di Torino 🇮🇹.