Generalization in deep learning remains poorly understood, as neural networks fall outside the framework of classical statistical learning theory. To make progress on this question, research has focused on controlled tasks, such as modular addition, as a testbed for generalization. On this task, models exhibit grokking, i.e. a delayed onset of generalization after training loss has converged.
Mike Lee PhD, Associate Professor Department of Systems Biology, UMass Chan Medical School
*Talk Title:* Life, death, and the discovery of PDAR: the Pol II Degradation-dependent Apoptotic Response
*Abstract:* Many cellular functions are considered “life essential”, but why are they actually essential? Why does a cell die, for instance, when transcription or translation are inhibited, and can we improve cancer therapies by developing a more complete understanding of how cellular life/death decisions are made? To answer these questions, we developed a suite of new tools for studying all forms of cell death.
Laurents Marker - Software developer, National Centre for Atmospheric Science
Laurents Marker, a software developer at the National Centre for Atmospheric Science, works as part of a team that provides weather forecasting, data visualisation and planning tools to operational and scientific teams during observation campaigns. His work is centred around developing and deploying web applications, but over the past year has become increasingly focussed on their performance and robustness. This talk will cover areas on both the client and the server where developer effort has greatly improved user experience and service quality.
Training generative AI is not a one-step process. In the case of large language models (LLMs), self-supervision is often followed by supervised and reinforcement learning stages to improve instruction following, safety, and other desirable qualities. This multi-stage process that has emerged in the last 3 years has led to huge leaps in model capabilities. It has also led to new challenges and risks. In this talk, I will overview some of our group's work to identify and address such challenges by focusing on the training data used at different stages.
Prof Isabelle Augenstein (University of Copenhagen)
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or correcting this embedded knowledge without the significant cost of retraining. Moreover, when using these language models for knowledge-intensive language understanding tasks, LMs have to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge.
In this talk, I will present CodeScaler, a novel framework designed to overcome the scalability bottlenecks of Reinforcement Learning from Verifiable Rewards (RLVR) in code generation. While traditional RLVR relies heavily on the availability of high-quality unit tests—which are often scarce or unreliable—CodeScaler introduces an execution-free reward model that scales both training and test-time inference.
We warmly invite you to the C2D3 Computational Biology Annual Symposium 2026. This event is open to everyone in the Computational Biology Community.
https://www.c2d3.cam.ac.uk/events/comp-bio-2026
Early Career Researcher: Abstract Submission
We are inviting Early Career Researchers to present their research during the symposium. Talks should be 17 minutes each, and a short Q&A will follow. Abstract submission - Deadline 9am 1st April 2026.
Registrations
Registration is essential. A waitlist will open if capacity is reached. Registrations - Deadline 9am Monday 4th May 2026.
Scientific discovery emerges not from isolated reasoning, but from the intersection of diverse epistemic traditions. This talk proposes that the modern AI ecosystem, a structured network of heterogeneous reasoning agents spanning approximate and rigorous inference, constitutes a new form of collaborative intelligence for scientific inquiry. Drawing on Simon's conception of reasoning as adaptive search, we argue that such ecosystems do not merely accelerate known reasoning pathways, but create conditions under which genuinely novel representations may emerge.
Scientific discovery emerges not from isolated reasoning, but from the intersection of diverse epistemic traditions. This talk proposes that the modern AI ecosystem, a structured network of heterogeneous reasoning agents spanning approximate and rigorous inference, constitutes a new form of collaborative intelligence for scientific inquiry. Drawing on Simon's conception of reasoning as adaptive search, we argue that such ecosystems do not merely accelerate known reasoning pathways, but create conditions under which genuinely novel representations may emerge.
Scientific discovery emerges not from isolated reasoning, but from the intersection of diverse epistemic traditions. This talk proposes that the modern AI ecosystem, a structured network of heterogeneous reasoning agents spanning approximate and rigorous inference, constitutes a new form of collaborative intelligence for scientific inquiry. Drawing on Simon's conception of reasoning as adaptive search, we argue that such ecosystems do not merely accelerate known reasoning pathways, but create conditions under which genuinely novel representations may emerge.
Kirsty Pringle - Software Sustainability Institute; EPCC, University of Edinburgh
Research Software Engineers (RSEs) collaborate with researchers to develop and maintain software, helping to embed best practices that improve reliability and reduce inefficiencies in research workflows.
As awareness grows of the environmental impact of computational research, a new specialism - Green RSE - is beginning to emerge.
Green RSEs integrate sustainability into software development, ensuring environmental considerations are addressed alongside performance and usability.
Abstract: Neural networks have shown remarkable performance across data domains, especially in regimes of increasing compute budgets. However, fundamental insights into how neural networks process information, share representations and traverse loss landscapes remain uncertain. In this work, we quantify the functional impact of distribution matching, facilitated by knowledge sharing mechanisms such as knowledge distillation, under student-teacher optimisation strategies.
