Related papers: EPEE: Towards Efficient and Effective Foundation M…
Foundation models (FMs) are driving a prominent shift in biomedical imaging from task-specific models to unified backbone models for diverse tasks. This opens an avenue to integrate imaging, pathology, clinical records, and genomics data…
Energy-Based Models (EBMs) have proven to be a highly effective approach for modelling densities on finite-dimensional spaces. Their ability to incorporate domain-specific choices and constraints into the structure of the model through…
Accurate cancer survival prediction requires integration of diverse data modalities that reflect the complex interplay between imaging, clinical parameters, and textual reports. However, existing multimodal approaches suffer from simplistic…
Training AI models that generalize across tasks and domains has long been among the open problems driving AI research. The emergence of Foundation Models made it easier to obtain expert models for a given task, but the heterogeneity of data…
By processing electronic health records (EHRs) as natural language sequences, large language models (LLMs) have shown potential in clinical prediction tasks such as mortality prediction and phenotyping. However, longitudinal or highly…
The surging amount of biomedical literature & digital clinical records presents a growing need for text mining techniques that can not only identify but also semantically relate entities in unstructured data. In this paper we propose a text…
Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively. Nested events involve a kind of Pivot Elements (PEs) that simultaneously act as arguments of…
The recent surge of foundation models in computer vision and natural language processing opens up perspectives in utilizing multi-modal clinical data to train large models with strong generalizability. Yet pathological image datasets often…
Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modules introduces substantial parameter memory,…
Deploying deep neural networks (DNNs) on resource-constrained mobile devices presents significant challenges, particularly in achieving real-time performance while simultaneously coping with limited computational resources and battery life.…
Current evaluation frameworks for foundation models rely heavily on static, manually curated benchmarks, limiting their ability to capture the full breadth of model capabilities. This paper introduces Active learning for Capability…
Recent advances in transformer architectures have revolutionised natural language processing, but their application to healthcare domains presents unique challenges. Patient timelines are characterised by irregular sampling, variable…
Foundation models hold significant promise in healthcare, given their capacity to extract meaningful representations independent of downstream tasks. This property has enabled state-of-the-art performance across several clinical…
Emergent intelligence have played a major role in the modern AI development. While existing studies primarily rely on empirical observations to characterize this phenomenon, a rigorous theoretical framework remains underexplored. This study…
Current inference systems for Mixture-of-Experts (MoE) models primarily employ static parallelization strategies. However, these static approaches cannot consistently achieve optimal performance across different inference scenarios, as they…
With the increasing adoption of AI applications such as large language models and computer vision AI, the computational demands on AI inference systems are continuously rising, making the enhancement of task processing capacity using…
We study the problem of subgroup discovery for survival analysis, where the goal is to find an interpretable subset of the data on which a Cox model is highly accurate. Our work is the first to study this particular subgroup problem, for…
Graphical User Interface (GUI) task automation constitutes a critical frontier in artificial intelligence research. While effective GUI agents synergistically integrate planning and grounding capabilities, current methodologies exhibit two…
Partial Differential Equations (PDEs) are the bedrock for modern computational sciences and engineering, and inherently computationally expensive. While PDE foundation models have shown much promise for simulating such complex…
The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization. However, this assumption oversimplifies the real…