Marvin Alberts

Bio

Marvin is a PhD student jointly at IBM Research and the University of Zürich. His research focusses on multimodal language models applied to analytical chemistry. Before joining IBM he completed a Masters in Chemistry at Imperial College London.

Publications

Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
- - Marvin Alberts
  - Oliver Schilter
  - et al.
- 2024
- NeurIPS 2024
A Multimodal Transformer Model for comprehensive Structure Elucidation
- - Marvin Alberts
  - Oliver Schilter
  - et al.
- 2024
- ACS Fall 2024
Multimodal Transformer models for Structure Elucidation from Spectra
- - Marvin Alberts
  - Alain Vaucher
- 2024
- ACS Spring 2024
Conformal Autoregressive Generation: Beam Search with Coverage Guarantees
- - Nicolas Deutschmann
  - Marvin Alberts
  - et al.
- 2024
- AAAI 2024
From Spectra to Structure: Automated structure elucidation for organic chemistry
- - Marvin Alberts
  - Teodoro Laino
  - et al.
- 2024
- DMCCB Basel Symposium 2024
Using Foundation Models to Promote Digitization and Reproducibility in Scientific Experimentation
- - Amol Thakkar
  - Andrea Giovannini
  - et al.
- 2023
- NeurIPS 2023
Learning the Language of NMR: Structure Elucidation from NMR spectra using Transformer Models
- - Marvin Alberts
  - Federico Zipoli
  - et al.
- 2023
- NeurIPS 2023
Unveiling the Secrets of ¹H-NMR Spectroscopy: A Novel Approach Utilizing Attention Mechanisms
- - Oliver Schilter
  - Marvin Alberts
  - et al.
- 2023
- NeurIPS 2023
Automatic structure elucidation from NMR spectra
- - Marvin Alberts
  - Federico Zipoli
  - et al.
- 2023
- ACS Fall 2023
Automatic structure elucidation from IR spectra
- - Marvin Alberts
  - Teodoro Laino
  - et al.
- 2023
- ACS Fall 2023

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.