Accelerate Lunchtime Seminar Series
Starts: 2026/06/01 at 12:00
Ends: 2026/06/01 at 13:00
Join us to find out more about research taking place in AI for Science across the Accelerate Science community.
Details of future talks are available on Talks@Cam
Lunch provided, registration is required, please register here.
AI meets cultural heritage: Non-invasive imaging and machine learning techniques for the reconstruction of degraded historical sheet music
Anna Breger, Project Leader, University of Cambridge
In this talk we discuss the potential of non-invasive imaging and machine learning techniques for the reconstruction of degraded medieval music notation. Our examples include manuscripts and fragments that suffer from different kinds of degradations rendering parts of the notation illegible. Such degradations may happen due to chemical or physical damage, for example from iron-gall acidity or from deliberate erasure. When appropriate for the problem at hand, multispectral imaging (MSI) has the power to envision the invisible, depending on the choice of post-processing for the visualization. We compare the images acquired from different MSI systems as well as traditional versus our advanced post-processing, and demonstrate the success on medieval manuscripts and fragments with musical notation from Oxbridge libraries. Lastly, we will shortly introduce our novel MSI processing toolbox, that will be publicly available soon.
Fine-Tuning Large Language Models on Multi-Turn Conversations for Cognitive Behavioral Therapy
Rishabh Balse, Department of Computer Science and Technology, University of Cambridge
Abstract coming soon
These seminars are open to members of the University of Cambridge. For further details, please email accelerate-science@cst.cam.ac.uk.