107 citations · 107 across the 7 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
Hao Lu, Onur C. Koyun, Yongxin Guo +3
Vector-quantized autoencoders deliver high-fidelity latents but suffer inherent flaws: the quantizer is non-differentiable, requires straight-through hacks, and is prone to collaps…
cs.LG2024
Do deep neural networks utilize the weight space efficiently?
Onur Can Koyun, Behçet Uğur Töreyin
Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in reso…