Carlos is an AI Researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, and AI Safety. He is particularly interested in developing trustworthy, accurate, and efficient vision and AI systems that can reliably perceive, understand, and act on information, while protecting privacy and aligning with societal values. Carlos received his Ph.D. with Laureate distinction from Universidad Industrial de Santander, Colombia, in 2022, under the supervision of Professor Henry Arguello. He has publications at top venues including CVPR, ICCV, ECCV, ACL, and IEEE journals such as TMI and JSTSP, and is a co-inventor on two US patents in privacy-preserving computer vision, one of which has since been issued (US 12,651,379 B2). His paper “Optics Lens Design for Privacy-preserving Scene Captioning” received the Best Paper Award at ICIP 2022, and his research has been featured as an oral presentation at several top conferences, including ICCV 2021, CVPR 2026, and ECCV 2026. He was a research intern at the Stanford Vision and Learning Lab (SVL) in 2021 and recently a visiting researcher at the Torr Vision Group at the University of Oxford. He currently leads the AI Safety research theme within IVUL and the research effort on the Competitive Research Grant (CRG) between KAUST and the University of Oxford on safe AI agents (“Safe Operating System Agents”). He has also co-organized the LXCV workshop at CVPR (2 times), ICCV (2 times), and ECCV (1 time), as well as the SaFeMM-AI workshop at ICCV 2025.