MPEGO: A toolkit for multi-level performance evaluation of generative models for material discovery domains
- Girmaw Abebe Tadesse
- Jannis Born
- et al.
- 2022
- KDD 2022
Bio
Matteo is a Senior Research Scientist in Accelerated Discovery at IBM Research Europe - Zürich. His research interests are AI-driven autonomous labs and multimodal generative models for material science. He received his degree in Mathematical Engineering from Politecnico di Milano in 2013. After getting his MSc, he worked in a startup, Moxoff spa, as a software engineer and analyst for scientific computing. In 2019 he obtained his doctoral degree at the end of a joint Ph.D. program between IBM Research and the Institute of Molecular Systems Biology, ETH Zürich, with a thesis on multimodal learning approaches for precision medicine.
Matteo's full publication record is available on Google Scholar.
Publications
A Fully Differentiable Set Autoencoder
- Nikita Janakarajan
- Jannis Born
- et al.
- 2022
- KDD 2022
PGT: a prompt based generative transformer for the patent domain
- Dimitrios Christofidellis
- Antonio Berrios Torres
- et al.
- 2022
- ICML 2022
PCfun: a hybrid computational framework for systematic characterization of protein complex function
- Varun S Sharma
- Andrea Fossati
- et al.
- 2022
- Briefings in Bioinformatics
Identification of Enzymatic Active Sites with Unsupervised Language Modeling
- Matteo Manica
- Loic Kwate Dassi
- et al.
- 2022
- ISGC 2022
Regression Transformer - Blending Numerical and Textual Tokens for Concurrent Property Predicition and Conditional Generation
- 2022
- MRS Spring Meeting 2022
Identification of enzymatic active sites with unsupervised language modelling
- Loic Kwate Dassi
- Matteo Manica
- et al.
- 2022
- MRS Spring Meeting 2022
Regression Transformer: Concurrent Conditional Generation and Regression by Blending Numerical and Textual Tokens
- 2022
- ICLR 2022
Multitask Prompted Training Enables Zero-Shot Task Generalization
- Victor Sanh
- Albert Webson
- et al.
- 2022
- ICLR 2022
Molecular transformer-aided biocatalysed synthesis planning
- Daniel Probst
- Matteo Manica
- et al.
- 2022
- ACS Spring 2022
Patents
- US
- 12124958
- US
- 11942189
- JP
- 7358005
- US
- 11651860
- US
- 11651841
- US
- 11515005
- GB
- 2595994
- US
- 11150926
- US
- 10593422
Projects
Lab that Learns
Leveraging AI foundation models and multi-cloud computing to usher in a new era of reproducible and collaborative experimentation for scientific discovery.
Accelerator Technologies
We're developing technological solutions to assist subject matter experts with their scientific workflows by enabling the Human-AI co-creation process.
AI for Scientific Discovery
Creating the AI-enabled lab for a new era of reproducible and collaborative experimentation
Blog posts
How generative AI models can fuel scientific discovery
ExplainerJohn R Smith and Matteo Manica6 minute readNeuNetS: Automating Neural Network Model Synthesis for Broader Adoption of AI
ResearchCristiano Malossi
Top collaborators
TL
Teodoro Laino
Distinguished RSM, Manager
GG
Gianmarco Gabrieli
Pre-Doctoral Researcher
JB
Jannis Born
Research Scientist in AI for Scientific Discovery
FZ
Federico Zipoli
Research Scientist