Artificial Intelligence Research Group Talks

Abstract not available

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...

The increasing availability and resolution of spatially resolved sequencing on human tissue samples, such as Spatial Transcriptomics (ST), provides rich and spatially resolved molecular information to diagnose and analyse tumours beyond the morphological information routinely available to pathologists through Whole Slide...

In training language models, training choices—such as the random seed for data ordering or the token vocabulary size—significantly influence model behaviour. Answering counterfactual questions like "How would the model perform if this instance were excluded from training?" is computationally expensive, as it requires re-...

Diversity has been shown to be key to collective intelligence in natural systems. Despite this, current Multi-Agent Reinforcement Learning (MARL) approaches enforce behavioral homogeneity (to boost efficiency) or blindly promote behavioral diversity via intrinsic rewards or additional loss functions, effectively changing...