Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Memory-Efficient Training with In-Place FFT Implementation
Xinyu Ding, Bangtian Liu, Siyu Liao +1
Fast Fourier Transforms (FFT) are widely used to reduce memory and computational costs in deep learning. However, existing implementations, including standard FFT and real FFT (rFF…
cs.LG2025
CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
Xuchen Feng, Siyu Liao
Normalizing flows are deep generative models that enable efficient likelihood estimation and sampling through invertible transformations. A key challenge is to design linear layers…
cs.LG2025
Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors
Xinyu Ding, Lexuan Chen, Siyu Liao +1
Foundation models have achieved tremendous success in different domains. However, their huge computation and storage complexity make these models difficult to fine-tune and also le…