Gabriele Corso

PhD student, MIT

gcorso@mit.edu

Bio

I'm an second-year PhD student at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) co-advised by Tommi Jaakkola and Regina Barzilay. My research focuses on geometric deep learning and generative models and their application to challenging problems in biochemistry and physics.

I did my Bachelor at the University of Cambridge where I wrote my thesis under the supervision of Pietro Lió and Jure Leskovec. Previously, I interned at Twitter Research, D.E. Shaw and Alchera Technologies as a machine learning researcher and at IBM and STMicroelectronics as a software engineer.

I am also part of the core team and mentor at LeadTheFuture, a nonprofit organization helping talented Italian university and high school students reach their potential.

Publications

Most recent publications on Google Scholar.
indicates equal contribution.

Modeling Molecular Structures with Intrinsic Diffusion Models

Gabriele Corso

MIT Master's Thesis.

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Gabriele Corso, Hannes Stärk, Bowen Jing, Regina Barzilay, Tommi Jaakkola

ICLR 2023 and Best Student Paper Award at the NeurIPS 2022 Score-Based Modeling workshop.

Torsional Diffusion for Molecular Conformer Generation

Bowen Jing, Gabriele Corso, Jeffrey Chang, Regina Barzilay, Tommi Jaakkola

NeurIPS 2022. Oral presentation.

Subspace Diffusion Generative Models

Bowen Jing, Gabriele Corso, Renato Berlinghieri, Tommi Jaakkola

ECCV 2022.

Neural Distance Embeddings for Biological Sequences

Gabriele Corso, Rex Ying, Michal Pándy, Petar Veličković, Jure Leskovec, Pietro Liò

NeurIPS 2021.

Directional Graph Networks

Dominique Beaini, Saro Passaro, Vincent Létourneau, William L. Hamilton, Gabriele Corso, Pietro Liò

ICML 2021. Oral presentation.

Principal Neighbourhood Aggregation for Graph Nets

Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković

NeurIPS 2020.

EigenFold: Generative Protein Structure Prediction with Diffusion Models

Bowen Jing, Ezra Erives, Peter Pao-Huang, Gabriele Corso, Bonnie Berger, Tommi Jaakkola

ICLR MLDD workshop 2023.

Modeling Molecular Structures with Intrinsic Diffusion Models

Gabriele Corso

MIT Master's Thesis.

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Gabriele Corso, Hannes Stärk, Bowen Jing, Regina Barzilay, Tommi Jaakkola

ICLR 2023 and Best Student Paper Award at the NeurIPS 2022 Score-Based Modeling workshop.

Torsional Diffusion for Molecular Conformer Generation

Bowen Jing, Gabriele Corso, Jeffrey Chang, Regina Barzilay, Tommi Jaakkola

NeurIPS 2022. Oral presentation.

Subspace Diffusion Generative Models

Bowen Jing, Gabriele Corso, Renato Berlinghieri, Tommi Jaakkola

ECCV 2022.

Graph Anisotropic Diffusion

Ahmed A. A. Elhag, Gabriele Corso, Hannes Stärk, Michael M. Bronstein

ICLR 2022 Workshop on Geometrical and Topological Representation Learning.

3D Infomax improves GNNs for Molecular Property Prediction

Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Liò

ICML 2022.

Learning Graph Search Heuristics

Michal Pándy, Weikang Qiu, Gabriele Corso, Petar Veličković, Zhitao Ying, Jure Leskovec, Pietro Lio

LoG 2022.

Neural Distance Embeddings for Biological Sequences

Gabriele Corso, Rex Ying, Michal Pándy, Petar Veličković, Jure Leskovec, Pietro Liò

NeurIPS 2021.

Directional Graph Networks

Dominique Beaini, Saro Passaro, Vincent Létourneau, William L. Hamilton, Gabriele Corso, Pietro Liò

ICML 2021. Oral presentation.

Principal Neighbourhood Aggregation for Graph Nets

Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković

NeurIPS 2020.

Vitæ

Here is a copy of my CV.

Acknowledgements

This website uses the website design and template by Martin Saveski.