Dumoulin et al. (2017) modify the way class conditioning is passed to G by supplying it with class-conditional gains and biases in BatchNorm (Ioffe & Szegedy, 2015) layers. In Miyato & Koyama (2018), D is conditioned by using the cosine sim…Yuhuai Wu, Yuri Burda, Ruslan Salakhutdinov, and Roger B. Grosse. On the quantitative analysis of decoder-based generative models. In ICLR, 2017.
Yasin Yazc, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, and Vijay Chand…
Yuhuai Wu
scientist · 2 mentions across 1 reading
In this course
Yuhuai Wu is a researcher who contributed to understanding how decoder-based generative models work quantitatively, a foundational question for evaluating and improving generative architectures in machine learning. The course readings cite Wu et al.'s 2017 ICLC paper on decoder-based generative models in the context of discussing various conditioning mechanisms in GANs, suggesting his work helps ground architectural choices in theoretical analysis rather than purely empirical intuition.
Mentioned in 1 reading
Appears alongside
People mentioned in the same passages — sorted by co-occurrence weight.
Augustus Odena 1Chuan-Sheng Foo 1Dimitris Metaxas 1Georgios Piliouras 1Han Zhang 1Ian Goodfellow 1Karen Simonyan and Andrew Zisserman 1Kim-Hui Yap 1Roger B. Grosse 1Ruslan Salakhutdinov 1Stefan Winkler 1Vijay Chandrasekhar 1Yasin Yazc 1Yuri Burda 1Christian Szegedy 1Dumoulin 1Lucas Theis 1Martin Heusel 1Masashi Koyama 1Maurice Fréchet 1Mikołaj Bińkowski 1Rishi Sharma 1Sergey Ioffe 1Shane T. Barratt 1Takeru Miyato 1Tim Salimans 1