Research team proposed MDIDCN, a dual-channel network model for predicting miRNA-drug interactions (MDIs). Using TCN and BiLSTM, their model achieved high accuracy.

Research team proposed new data placement algorithms for scratch-pad memory (SPM) in embedded systems. Their fine-grained and multi-granularity algorithms effectively reduce data transfer and access latency, addressing inconsecutive array access and memory activation overhead.

Research team proposed an efficient algorithm for model diagnostics. Their method approximates the ranking of failure probabilities for components, achieving high accuracy and significant runtime improvements over existing algorithms.

Research team from Shandong University introduced MetaGIN, a lightweight deep learning framework for molecular property prediction. MetaGIN achieves SOTA performance with fewer parameters, using a “3-hop convolution” technique and MetaFormer architecture to balance efficiency and accuracy.

Research team introduced a new interpretation method for tree models based on feature group importance. Their method uses BGShapvalue and BGShapTree to capture complex correlations.

A team from EPCC proposed FLAPS, a fluctuation-aware power auction strategy to optimize data center power utilization. FLAPS reduces power overload by 9%–10% while maintaining high resource utilization.

A landmark study by WEHI scientists has shed new light on one of the most fundamental mysteries of biology: how cells divide and grow into the complex structures that make up our bodies.

The study has produced a sophisticated and leading new technology for tracking cells very early during embryo development, as they divide, migrate and specialise into the organs, tissues and systems that keep us alive.

The innovative tech, called LoxCode, provides each cell in a genetically engineered mouse with one of billions of individual DNA barcodes, allowing them to be tracked in unprecedented detail.