Scholar
Emanuele Palumbo
Google Scholar ID: Y7VFjEpEmyoC
PhD Student, ETH Zürich
Citations & Impact
Citations
202
H-index
5
i10-index
5
Publications
10
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published several papers including 'Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders' at ICLR 2024 and 'Efficient Bayesian Heteroscedastic Regression with Deep Neural Networks' at NeurIPS 2023. Recipient of the highly competitive ETH AI Center Doctoral Fellowship.
Research Experience
- Works on diverse problems in deep learning, focusing on designing generative models that handle a large set of diversified data modalities, balancing generative quality with semantic alignment. Also explores self-supervised learning, clustering, and modeling hierarchies in the data. Organizer and Program Chair of the Time Series Representation Learning for Health workshop at ICLR 2023, and the Deep Generative Models for Health workshop at NeurIPS 2023.
Education
- MSc in Data Science from ETH Zurich, Switzerland; BSc in Computer and Automation Engineering from Università Politecnica delle Marche
Background
- Ph.D. student in Computer Science at ETH Zurich, Doctoral Fellow at the ETH AI Center, and part of the Medical Data Science Lab led by Prof. Julia Vogt. Currently on a Machine Learning Research Internship in Health AI at Apple AIML. Research interests include multimodal learning, generative models, representation learning, Bayesian methods, and AI for health.
Miscellany
- Passionate about making voice and guitar acoustic covers, enjoys outdoor activities, particularly windsurfing and sailing.
Co-authors