Abstract:

Abstract: If we want to build collaborative language models, we'll need to find the right training objective. One promising direction involves simulating human users at scale and using these simulations as a training signal to develop models that better understand and interact with people. In this talk, I’ll discuss key challenges in simulating human behavior, ranging from hallucinations and coherence to knowledge consistency and memory. Then, I’ll discuss some recent and ongoing work and outline future directions for building more human-like user simulators.

Abstract:

Programming languages are diverging. Each is decades ahead of or behind the others, depending on the features of interest. This talk will present modern Fortran's leading role in language support for distributed-memory parallel programming, modular programming, array programming, GPU programming, and type-safe generic programming.

There has been a lot of excitement around "LLM agents", but how capable are they in open-ended multi-agent coordination problems?

To study this, we designed a long-horizon, open-ended multi-agent coordination environment and compared zero-shot LLM agents with trained MARL agents. We find that the two paradigms have distinct strengths and limitations, highlighting that coordination is a bottleneck separate from standard long-horizon task competence.

The Careers Beyond Academia Seminar Series provides PhD students and Early Career Researchers with realistic, experience-based insights into career pathways outside academia. Through invited talks from professionals working across industry and organisations, the series helps researchers understand how to successfully transition their skills and expertise into impactful roles beyond the university environment.

Abstract:

This free event is open only to members of the University of Cambridge (and affiliated institutes). Please be aware that we are unable to offer consultations outside clinic hours.

If you would like to participate, please sign up as we will not be able to offer a consultation otherwise. Please sign up through the following link: https://forms.gle/HdHM5kKYuxcdRPzr6. Sign-up is possible from June 18 midday (12pm) until June 22 midday or until we reach full capacity, whichever is earlier. If you successfully signed up, we will confirm your appointment by June 24 midday.

Abstract: Current AI training methods align models with human values only after their core capabilities have been established, resulting in models that are easily misaligned and lack deep-rooted value systems. We propose a paradigm shift from "model training" to "model raising", in which alignment is woven into a model's development from the start.

Abstract:

Estimators assuming missingness at random (MAR) can fail under missingness not at random (MNAR). Introducing complete auxiliary variables sometimes restores MAR by breaking dependence between analysis variables and missingness. However, if the auxiliaries are themselves incomplete, MAR typically remains violated.

Sign up on Eventbrite: https://medai-july2026.eventbrite.co.uk