Razvan Marinescu

Razvan Marinescu is an Assistant Professor in the Department of Computer Science and Engineering at the University of California Santa Cruz, where he leads a research lab focused on machine learning for healthcare, biomolecular systems, and neuroimaging. He is also the co-founder and CTO of GiwoTech Inc., a drug screening startup.

Education:

• PostDoc, MIT CSAIL, Polina Golland’s Lab
• PhD in Computer Science, 2019, Center for Medical Image Computing, University College London
• MEng in Computer Science, 2014, Imperial College London
• BSc in Computer Science, 2013, Imperial College London

Razvan's research spans machine learning, Bayesian inference, generative models, and their applications in medicine and molecular biology. His work includes modeling neurodegenerative diseases like Alzheimer’s and Posterior Cortical Atrophy, developing differentiable simulators for MRI, and advancing generative AI for medical image reconstruction and drug discovery. He has a strong interest in the mathematical foundations of statistical inference in machine learning.

His recent publications demonstrate a strong trend toward using deep generative models, diffusion models, and Bayesian frameworks for solving inverse problems in medical imaging and simulating biological systems. Key themes include super-resolution MRI, microstructure reconstruction, and applying Malliavin calculus to diffusion models.

Scientific Awards:

• Best Paper Award, NeurIPS Deep Generative Models and Downstream Applications Workshop (2021)

Razvan advises a large group of PhD and master’s students and has secured significant research visibility through community challenges like TADPOLE. He has also contributed to open-source tools such as BrainPainter and actively collaborates with institutions worldwide. His lab receives support through academic grants and entrepreneurial funding via his startup.

Labs and Projects: He leads a research group at UC Santa Cruz focusing on projects including AI for Material Science, Simulating a Virtual Cell, ML Compositionality, Image Reconstruction, Generative Modeling, ML Benchmarks, Disease Progression Modeling, Differentiable Simulators, ML for Molecular Dynamics, and Medical Visualization.