PhD Student, University of Toronto
Senior Autonomy Engineer, Uber ATG
Email: email@example.com, firstname.lastname@example.org
Mengye Ren is a PhD student in the machine learning group of the Department of Computer Science at the University of Toronto. His academic advisor is Prof. Richard Zemel. He also works part-time at Uber Advanced Technologies Group (ATG) Toronto, directed by Prof. Raquel Urtasun, doing research related to self-driving. During his undergrad, he studied Engineering Science with a focus on Electrical and Computer Engineering at the University of Toronto. He is originally from Shanghai, China.
Deep learning, machine learning, computer vision
One paper got accepted to ICLR 2019!
I will be teaching CSC 411 (Machine Learning and Data Mining) in the winter semester of 2019. [course website]
I will visit INRIA Grenoble Rhône-Alpes on July 19, 2018.
I will visit TU Berlin on July 16, 2018.
I will visit NEC lab in Princeton, NJ on June 4, 2018.
I will visit the University of Tübingen and MPI for Intelligent Systems from June 25 to July 20, 2018.
One paper got accepted to ICML 2018!
One paper got accepted to CVPR 2018!
Google Scholar [link]
Graph HyperNetworks for Neural Architecture Search. Chris Zhang, Mengye Ren, Raquel Urtasun. ICLR, 2019. [arxiv]
Learning to Reweight Examples for Robust Deep Learning. Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun. ICML, 2018. [arxiv]
Meta-Learning for Semi-Supervised Few-Shot Classification. Mengye Ren, Eleni Triantafillou
*, Sachin Ravi
*, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. ICLR, 2018. [link][arxiv] [code]
ECE 521: Inference Algorithms (2017 Winter)
CSC 401/2511: Natural Language Computing (2016 Winter)
CSC 190: Data Structure and Algorithm (Engineering Science) (2014 Winter)
TensorFlow Forward AD: Forward-mode automatic differentiation for TensorFlow. [github]
PySched: Python-based light weight pipeline scheduler for local and slurm jobs. [github]
Deep Dashboard: Visualize training process in real time. [github]
Meta-Learning for Weakly Supervised Learning. INRIA Grenoble Rhône-Alpes. Grenoble, France. 2018/07. [slides]
Learning to Reweight Examples for Robust Deep Learning. Stockholm, Sweden. 2018/07. [slides]
Meta-Learning and Learning to Reweight Examples. Max Planck Institute for Intelligent Systems. Tübingen, Germany. 2018/06. [slides]
Meta-Learning for Weakly Supervised Learning. NEC Laboratories America. Princeton, NJ, USA. 2018/06. [slides]
SBNet: Sparse Blocks Network for Fast Inference. Borealis AI Lab. 2018/02. [slides]
Meta-Learning for Semi-Supervised Few-Shot Classification. Vector Institute. 2017/11. [slides]
Sequence-to-Sequence Deep Learning with Recurrent Attention. Queen's University. 2017/05. [slides]
Deep Dashboard Tutorial. University of Toronto. 2016/02. University of Guelph. 2016/03. [slides]
Exploring Data and Models for Image Question Answering. Lille, France. ICML 2015 Deep Learning Workshop. 2015/07. [slides]
Autonomous vehicles: U of T researchers make advances with new algorithm. Nina Haikara. U of T News. 2018/06/21. [link]
Industry | Uber proposed SBNet: Leveraging Activation Block Sparsity for Speeding up Convolutional Neural Networks 业界 | Uber提出SBNet：利用激活的稀疏性加速卷积网络 (Article in Chinese). Synced. 2018/01/18. [link]
SBNet: Leveraging Activation Block Sparsity for Speeding up Convolutional Neural Networks. Uber Engineering Blog. 2018/01/16. [link]