by Cardiff University

edited by Lisa Lock, reviewed by Andrew Zinin

Editors' notes

The GIST

Add as preferred source

Credit: Pixabay/CC0 Public Domain

Researchers at Cardiff University have presented two studies at the 2026 International Conference on Machine Learning (ICML 2026) that address fundamental challenges in modern AI: understanding the complex geometry and relationships within data and recognizing patterns that occur across very different scales.

Dr. You Zhou, senior lecturer at Cardiff University's School of Medicine and senior author of the studies, said, "Biological research generates enormous amounts of complex data, but much of today's AI still struggles to understand the way biological systems are naturally organized. Cells interact within tissues, and important patterns can appear at many different scales.

"Our research addresses these challenges by developing AI methods that can better understand both the geometry of biological data and the relationships between local details and larger-scale structures."

Vector Bundle Attention (VBA)—Teaching AI to understand the geometry of biology

In the first paper, "VBA: Vector Bundle Attention for intrinsically geometric representation learning," the researchers introduce Vector Bundle Attention (VBA), a new AI architecture that rethinks how machines compare and interpret information.

"Most current advanced AI systems are built on transformers, which use a mechanism to determine how different pieces of information relate to one another. While highly effective, conventional attention mechanisms do not naturally account for the geometric structure that underlies many forms of complex data," added Zhou.

The geometric limitations of AI are particularly important in biology, where individual cells are not isolated pieces of data. They exist within intricate molecular and spatial relationships that influence how tissues function and diseases develop.

The VBA model incorporates geometric relationships directly into the AI's attention mechanism, aligning information from cells according to their underlying geometry before making comparisons when modeling biological systems.

To test the VBA model, the researchers used single-cell RNA sequencing and spatial transcriptomics—technologies that enable scientists to examine the molecular characteristics of individual cells and understand how cells are organized within tissues. The VBA model achieved state-of-the-art performance in single-cell RNA sequencing tasks, strong performance in spatial transcriptomics and competitive results on 3D datasets, highlighting its potential beyond biomedical applications.

Dynamic Fractal Mamba—Helping AI see both detail and context

In a second paper, "Dynamic Fractal Mamba: A neural renormalization group flow for scale-invariant sequence modeling," the second AI model, Dynamic Fractal Mamba (DF-Mamba), tackles another major challenge in AI—understanding information across dramatically different scales.

"Many AI systems struggle to generalize when trained on relatively small data segments and then applied to much larger datasets. In biomedical research, this is a significant issue," said Zhou.

Inspired by concepts from physics used to describe how systems behave across scales, DF-Mamba repeatedly applies the same learned rules as it moves from smaller to increasingly larger patterns. This enables the model to integrate information within broader contexts efficiently.

The DF-Mamba model learns from smaller-scale data and can successfully analyze much larger-scale datasets that it has never previously encountered, without requiring retraining.

The two new approaches tackle current challenges when using AI to understand biological data, including how information is geometrically related and how patterns are connected across different scales.

Zhou said, "What is particularly exciting is that challenges arising from biomedical research have inspired new developments in AI itself. Research motivated by biomedical challenges can contribute not only to biomedical science, but also to fundamental advances in AI.

"We hope these approaches will ultimately give scientists more powerful tools to understand complex biological systems and help advance precision medicine."

More information

First paper: VBA: Vector Bundle Attention for intrinsically geometric representation learning

Second paper: Dynamic Fractal Mamba: A neural renormalization group flow for scale-invariant sequence modeling

Key concepts

Artificial neural networksFractals

Provided by Cardiff University

Who's behind this story?

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile ?

Andrew Zinin

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile ?