At VRAIN, research in machine learning and deep learning encompasses visual artificial intelligence, deep neural networks, and advanced perception systems. Work in this area spans computer vision for image and video analysis, multimodal interaction systems that combine visual, audio, and textual information, and immersive technologies including virtual reality (VR), augmented reality (AR), and extended reality (XR).

Neural network-based models developed at VRAIN support speech recognition and synthesis across multiple languages, including Spanish, Valencian, English, German, Portuguese, Italian, Dutch, French, and Slovenian. The group also develops explainable AI systems for model interpretation, data mining and analysis tools, and recommendation systems. AI evaluation frameworks are used to assess model quality and identify failure modes under real-world operating conditions, with applications in intelligent tutoring systems and serious games for education and training.