Prehistory — From Neural Networks to the TransformerJun-Yan Zhu et al. (UC Berkeley)UC Berkeley

Zhu et al. publish CycleGAN on arXiv

CycleGAN released on arXiv — domain translation with unpaired data

Why it matters

A design that trains without paired data, lowering the data requirements of generative models

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1703.10593

Added in Week 35, 2026 · See that week

Nearby on the same axis

In-Datacenter Performance Analysis of a Tensor Processing UnitPaperFinn, Abbeel and Levine publish Model-Agnostic Meta-Learning (MAML) on arXivPaperConvolutional Sequence to Sequence Learning (ConvS2S) released on arXivPaperArjovsky, Chintala and Bottou publish Wasserstein GAN on arXivPaper