{"id":11114,"date":"2026-05-27T15:28:43","date_gmt":"2026-05-27T13:28:43","guid":{"rendered":"https:\/\/cidai.eu\/generative-models-creating-to-anticipate-the-future\/"},"modified":"2026-06-10T09:29:15","modified_gmt":"2026-06-10T07:29:15","slug":"generative-models-creating-to-anticipate-the-future","status":"publish","type":"post","link":"https:\/\/cidai.eu\/en\/generative-models-creating-to-anticipate-the-future\/","title":{"rendered":"Generative models: creating to anticipate the future"},"content":{"rendered":"

Over the past ten years, generative models have gone from being a promising line of research in machine learning (ML) to becoming one of the core technologies of artificial intelligence (AI). Their evolution has been so rapid that in just a decade they have gone from generating experimental results to producing synthetic text, images, audio, video, and data <\/strong>with a level of realism and utility that is already transforming entire sectors.<\/p>\n

Initially, architectures such as variational autoencoders (VAEs) <\/strong>and Generative<\/strong> adversarial networks (GANs) stood out, capable of generating realistic synthetic images and data. <\/strong>Later, Transformer-based<\/strong> models gained prominence, currently forming the core architecture of large language models ( LLMs ). <\/strong>More recently, diffusion models have significantly improved the quality, variety, and control over results in domains such as audio and video. Today, we see these architectures combined in innovative ways in many AI models, in a vibrant race for the highly realistic generation of synthetic data <\/strong>. This is turning science fiction into reality in the development of diverse scientific and technological applications, from automation <\/strong>and industrial simulation <\/strong>to healthcare <\/strong>and robotics <\/strong>. Even with the emergence of new challenges related to privacy, bias, transparency, and trust, the expansion of this unstoppable technology, with its ever-increasing economic and social impact, has not been hindered.<\/p>\n

Beyond the now commonplace LLMs like ChatGPT, the generation of synthetic data is expanding research and development in areas of social value<\/strong>, for example, by facilitating data exchange for science, health, and public policy. This is the case when preserving the privacy of sensitive data<\/strong>, or when helping to balance the representation of data from infrequent situations<\/strong>, emergencies<\/strong>, or under-observed populations <\/strong>to improve the training of systems that must operate beyond the average scenario, as is being done in autonomous driving systems for accident prevention.<\/p>\n

However, a lesser-known facet of generative models is their enormous predictive potential. Their ability to learn unsupervised<\/strong>, without annotation, extremely complex data distributions\u2014which are difficult to explicitly model at a human scale\u2014is demonstrating their skill in predicting future situations based on certain initial conditions, a key functionality in many innovative applications. Let’s look at some examples:<\/p>\n