activity
20242026
collaborators

5 papers

cs.LG2026

A Geometric Lens on Physics-Aligned Data Compression

Aleix Segui, Wesley Armour

In AI for Science, physics-informed losses are increasingly used to train learned compressors for scientific data, but their rate-distortion implications remain poorly understood.…

cs.LG2026

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training

Yishun Lu, Wesley Armour

Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens of thousands of training samples. However, most existi…

cs.CV2025

Adaptive Illumination-Invariant Synergistic Feature Integration in a Stratified Granular Framework for Visible-Infrared Re-Identification

Yuheng Jia, Wesley Armour

Visible-Infrared Person Re-Identification (VI-ReID) plays a crucial role in applications such as search and rescue, infrastructure protection, and nighttime surveillance. However,…

cs.CV2024

Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy

Zeyu Yang, Karel Adamek, Wesley Armour

Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is…

cs.DC2024

Part-time Power Measurements: nvidia-smi's Lack of Attention

Zeyu Yang, Karel Adamek, Wesley Armour

The GPU has emerged as the go-to accelerator for high throughput and parallel workloads, spanning scientific simulations to AI, thanks to its performance and power efficiency. Give…