Research Areas
Large-Scale Multimodal AI
Development of large-scale multimodal architectures for visual question answering, grounded language generation, image editing understanding, and generative AI. Foundation model research, with access to EuroHPC-scale infrastructure.
Machine Learning & Deep Learning for resilient, online, distributed and incremental models
Development of novel algorithms and architectures for supervised, unsupervised, and reinforcement learning, federated learning, model merging, and PEFT. Model maintenance and incremental update techniques for efficient deep learning solutions.
Medical Imaging
Deep Learning for Medical Image Analysis and Clinically Deployable Decision Support.
Computer Vision
Advanced algorithms for image and video analysis, object recognition, and scene understanding.
IoT & Embedded AI
Research and Design on advanced IoT systems, embedded AI and sensor integration.
Robotics & Human-Robot Interaction
Human-robot interaction, Embodied AI and autonomous systems for real-world applications.
Bioinformatics and AI for Precision Medicine
Bioinformatics, Computational Biology, and Multimodal Data Integration for Precision Medicine.
Advancing the State of the Art:
Our research contributes to the global knowledge base with cutting-edge publications in top-tier venues. Discover our latest findings, methodologies, and innovations that are shaping the future of AI and Computer Vision.
Proud to be Part of:
AImageLab is proud to be part of a vibrant research community, collaborating with esteemed institutions and organizations to drive innovation in AI and Computer Vision.
