Cameron Gordon

2 accepted papers

2026

SineLoRA∆: Sine-Activated Delta Compression

Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Paul Albert, Simon Lucey

AAAI 2026technical

Resource-constrained weight deployment is a task of immense practical importance. Recently, there has been interest in the specific task of Delta Compression, where parties each hold a common base model and only communicate compressed weight updates. However, popular parameter efficient updates such

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Efficient Learning with Sine-Activated Low-Rank Matrices

Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey

ICLR 2025poster

Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learning. These techniques significantly lower the number of parameters, striking a balance between compactness and performan…

Cited by 0 Source ↗PDF ↗Scholar ↗