Artificial Intelligence Research Group Talks

This talk will present an overview of efforts the UK government has been taking on AI over the past year, including the AI Research Resource, the AI Safety Summit, and with a focus on the AI Safety Institute (AISI). AISI is the world’s first state-backed organization focused on advanced AI safety for the public benefit...

Identifying key patterns of tactics implemented by rival teams, and developing effective responses, lies at the heart of modern football. However, doing so algorithmically remains an open research challenge. To address this unmet need, we propose TacticAI, an AI football tactics assistant developed and evaluated in close...

This talk supports the R255 Advanced Topics in Machine Learning course module on Multimodal Learning and provides a bird’s eye view of the rapidly evolving text-audio landscape, with a focus on music as a primary example of audio data. I will first present types of tasks that exist in this space, then discuss data curation...

I will present deep screening, an ultra-high-throughput approach leveraging the Illumina HiSeq platform for massively parallel sequencing, display, and affinity and kinetics screening at the level up to 109 individual RNA, XNA and protein interactions. Deep screening enabled the rapid discovery of 2-O-methyl-RNA aptamers...

Recent years have witnessed a surge of interest in applying ideas and machinery from machine learning to the design of networked systems. I will discuss my recent efforts to incorporate learning in the context of two fundamental computer networking challenges: routing and congestion control. Specifically, I will discuss...

Retrosynthesis planning is a fundamental challenge in chemistry which aims at designing reaction pathways from commercially available starting materials to a target molecule. Each step in multi-step retrosynthesis planning requires accurate prediction of possible precursor molecules given the target molecule and confidence...

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions, wherein users can correct mispredicted concepts and thus improve the model's...

Abstract not available

There is a curious trend in machine learning (ML): researchers developing the most capable large language models (LLMs) increasingly evaluate them using manual methods such as red teaming. In red teaming, researchers hire workers to manually try to break the LLM in some form by interacting with it. Similarly, some users...

Technological advances in medical data collection such as high-resolution histopathology and high-throughput genomic sequencing have contributed to the rising requirement for multi-modal biomedical modelling, specifically for image, tabular, and graph data. Most multi-modal deep learning approaches use modality-specific...