Ruixiang Zhang
Scholar Github Twitter
June 2022


I am a PhD student at Mila and University of Montreal, co-supervised by Liam Paull and Yoshua Bengio. I enjoy working on generalizable and scalable representation learning, generative models, and unsupervised learning. During my PhD, I have also spent time working with amazing researchers from Microsoft Research, Google Brain, Apple, and Preferred Networks. Previously, I obtained my MPhil's degree at HKUST and my Bachelor's degree at Zhejiang University.


[Preprint] Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
Ting Chen, Ruixiang Zhang, Geoffrey Hinton

[Preprint] Robust and Controllable Object-Centric Learning through Energy-based Models
Ruixiang Zhang, Tong Che, Boris Ivanovic, Renhao Wang, Marco Pavone, Yoshua Bengio, Liam Paull

[ICLR] Learning Representation from Neural Fisher Kernel with Low-rank Approximation
Ruixiang Zhang, Shuangfei Zhai, Etai Littwin, Joshua M. Susskind

[Preprint] An Attention Free Transformer
Shuangfei Zhai, Walter Talbott, Nitish Srivastava, Chen Huang, Hanlin Goh, Ruixiang Zhang, Josh Susskind

[NeurIPS] Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling
Tong Che*, Ruixiang Zhang*, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio

[ICML] Learning Structured Latent Factors from Dependent Data: A Generative Model Framework from Information-Theoretic Perspective
Ruixiang Zhang, Katsuhiko Ishiguro, Masanori Koyama

[ICML] Perceptual Generative Autoencoders
Zijun Zhang, Ruixiang Zhang, Zongpeng Li, Yoshua Bengio, Liam Paull

[AAAI] Deep Verifier: Verification of Deep Discriminative Models with Deep Generative Model
Gerry Che, Xiaofeng Liu, Site Li, Yubin Ge, Ruixiang Zhang, Caiming Xiong, Yoshua Bengio

[NeurIPS] MetaGAN: An Adversarial Approach to Few-Shot Learning
Ruixiang Zhang*, Tong Che*, Zoubin Ghahramani, Yoshua Bengio, Yangqiu Song

[VAST] Understanding Hidden Memories of Recurrent Neural Networks
Yao Ming, Shaozu Cao, Ruixiang Zhang, Zhen Li, Yuanzhe Chen, Yangqiu Song, Huamin Qu

[Preprint] Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
Tong Che*, Yanran Li*, Ruixiang Zhang*, R Devon Hjelm, Wenjie Li, Yangqiu Song, Yoshua Bengio