Gabriel Raya

Sony AIJADS ResearchCSAI Tilburg UniversityTU/e

📍 Tokyo, Japan

I am currently a Research Intern at Sony AI and a Ph.D. Candidate in Machine Learning at Tilburg University & TU/e. I am also a visiting researcher at the Donders Institute for Brain, Cognition and Behaviour, working under the guidance of Dr. Luca Ambrogioni. My research focuses on probabilistic deep generative models, with a particular emphasis in diffusion models. I am passionated about integrating principles from statistical physics and critical phenomena to enhance our understanding of particle generation and the emergence of complex phenomena such as memorization, learning, and generalization in both natural and artificial systems. This interdisciplinary approach not only deepens our understanding of generative models but also sheds light on the intricate processes underlying complex systems in nature.

Previous to my Ph.D., I obtained a Master's degree in Computer Science from Radboud University, where I researched unsupervised out-of-distribution detection applied to digital pathology with Twan van Laarhoven and Jasper Linmans. I was a visiting researcher at the Computational Pathology Group of the Radboud University Medical Center, where I did research on deep learning to analyze histopathology images with Witali Aswolinskiy and Francesco Ciompi.

news

Nov 25, 2024 I joined Sony AI Music Foundational Model Team as a Research Intern! ✨ 🙌 ⚡
Nov 11, 2024 Our workshop paper Memorization to Generalization: The Emergence of Diffusion Models from Associative Memory has been accepted as a contributed talk at SciForDL NeurIPS 2024!.
Nov 11, 2024 Our workshop paper Dynamic Negative Guidance of Diffusion Models: Towards Immediate Content Removal has been accepted at SafeGenAI NeurIPS 2024!.
Jan 11, 2024 Our paper Diffusion models for out-of-distribution detection in digital pathology has been accepted at the journal of Medical Image Analysis 2024!.
Nov 2, 2023 Our paper Spontaneous Symmetry Breaking in Generative Diffusion Models has been accepted at NeurIPS 2023!. For more info check our blog post and video talk.