Artificial Intelligence Research Group Talks

Code generation is one of the most active areas of application of Large Language Models (LLMs). LLMs lower barriers to writing code and accelerate development process, so much so there are now research projects and businesses powered largely by LLM code generation process. It is however important to realise that the...

I will introduce the All-atom Diffusion Transformer (ADiT), a unified generative modelling architecture capable of jointly modelling both periodic crystals and non-periodic molecular systems. ADiT is a latent diffusion model that embeds 3D atomic systems into a shared latent space, where it learns to sample new latents and...

Conventional AI benchmarks typically focus on the content of responses, for example checking factual (e.g. MMLU) or mathematical correctness (e.g. GSM8k). However, for many language model applications, the manner (or "personality") of a model's responses also matters to users, for example how friendly or confident...

The seminar will be an interdisciplinary journey between applications of Artificial Intelligence (AI) Computer Vision based methods to the field of Forensics and Biomedical Imaging. I will first focus on AI applications for country recognition and city verification, presenting two works in which AI based models have been...

Explainability plays a pivotal role in building trust and fostering the adoption of artificial intelligence (AI) in healthcare, particularly in high-stakes domains like neuroscience where decisions directly affect patient outcomes. While progress in AI interpretability has been substantial, there remains a lack of clear...

Tree-based models are often robust to uninformative features and can accurately capture non-smooth, complex decision boundaries. Consequently, they often outperform neural network-based models on tabular datasets at a significantly lower computational cost. Nevertheless, the capability of traditional tree-based ensembles...

This talk supports the R255 Advanced Topics in Machine Learning 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...

In natural language, there are usually many ways to say the same thing: the answer to a question can be said multiple ways, and there are many good translations of the same sentence. As a result, language models (LMs) trained on large corpora often spread probability mass across a vast number of generations, containing...

Generative models see increasing use in computer-aided drug design. However, while performing well at capturing distributions of molecular motifs, they often produce synthetically inaccessible molecules. To address this, we introduce SynFlowNet, a GFlowNet model whose action space uses chemical reactions and buyable...

Transformers have recently sparked significant interest in AI, driving advancements in accuracy and enabling a wide range of applications, from multi-modal intelligent assistants to autonomous systems. While their scaling laws promise even greater capabilities, the demands on hardware and data present significant...