University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > An Introduction to In-Context Learning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

An Introduction to In-Context Learning

Download to your calendar using vCal

If you have a question about this talk, please contact .

Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.

In-context learning (ICL) has emerged as a powerful capability of large language models (LLMs), allowing them to adapt to new tasks without explicit parameter updates. This talk begins with an introduction to meta-learning and neural processes, which lay the foundation for ICL . We then move on to transformer based ICL where the model can be trained from scratch or leverage pre-trained LLMs. To attempt to understand why ICL works, we discuss its connections to Bayesian inference, kernel regression, and gradient descent. Finally, we examine potential safety concerns in ICL , highlighting risks and challenges in reliable AI deployment.

This talk is part of the Machine Learning Reading Group @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Gatsby Room (Chancellor's Centre), Wolfson College, Barton Road, Cambridge & Teams Rooms SG1 & SG2, Alison Richard Building, 7 West Road, Cambridge, CB3 9DT Room GS5 Donald McIntyre Building, Faculty of Education, 184 Hills Road, Cambridge

Other talks

Argentina 2005 Title to be confirmed Title TBC TBC Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge Reproducibility In Astrophysical Simulations: The AGORA Initiative and a 14-Year Human Experiment (In Memory of Joel Primack)
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity