ML, DL, LLMs, LVMs, TensorFlow, GCP, Pytorch, Python.
I am a PhD in Artificial Intelligence specialized in the areas of robotics, automatic planning and machine learning. In addition, I am organizer of T3chfest and Madrid Google Cloud Developer group, speaker at different meetups and GDE on Machine Learning.
Talks · 1
Vision-Language Models (VLMs) are a new class of Artificial Intelligence systems that combine computer vision with natural language processing. In this talk, we will explore how these models can understand and generate natural language from images, videos, and other visual data, enabling groundbreaking applications such as intelligent visual assistants, automatic captioning, and semantic scene understanding. I will also describe the fundamental principles behind their architecture and show how they can be used if you are crazy enough to build your own applications.