Picture for Zeming Lin

Zeming Lin

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Dec 03, 2019
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, Soumith Chintala

Figure 1 for PyTorch: An Imperative Style, High-Performance Deep Learning Library

Figure 2 for PyTorch: An Imperative Style, High-Performance Deep Learning Library

Figure 3 for PyTorch: An Imperative Style, High-Performance Deep Learning Library

* 12 pages, 3 figures, NeurIPS 2019

Access Paper or Ask Questions

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

Nov 30, 2018
Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier

Figure 1 for Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

Figure 2 for Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

Figure 3 for Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

Figure 4 for Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

* Advances in Neural Information Processing Systems 31 (2018) 10759-10770

Access Paper or Ask Questions

Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play

Apr 27, 2018
Sainbayar Sukhbaatar, Zeming Lin, Ilya Kostrikov, Gabriel Synnaeve, Arthur Szlam, Rob Fergus

Figure 1 for Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play

Figure 2 for Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play

Figure 3 for Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play

Figure 4 for Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play

* Published in ICLR 2018

Access Paper or Ask Questions

STARDATA: A StarCraft AI Research Dataset

Aug 07, 2017
Zeming Lin, Jonas Gehring, Vasil Khalidov, Gabriel Synnaeve

Figure 1 for STARDATA: A StarCraft AI Research Dataset

Figure 2 for STARDATA: A StarCraft AI Research Dataset

Figure 3 for STARDATA: A StarCraft AI Research Dataset

Figure 4 for STARDATA: A StarCraft AI Research Dataset

* To be presented at AIIDE17

Access Paper or Ask Questions

DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

Apr 17, 2017
Ji Gao, Beilun Wang, Zeming Lin, Weilin Xu, Yanjun Qi

Figure 1 for DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

Figure 2 for DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

Figure 3 for DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

Figure 4 for DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

* adversarial samples, deep neural network

Access Paper or Ask Questions

Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

Nov 26, 2016
Nicolas Usunier, Gabriel Synnaeve, Zeming Lin, Soumith Chintala

Figure 1 for Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

Figure 2 for Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

Figure 3 for Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

* 18 pages, 1 figure (2 plots), 2 tables

Access Paper or Ask Questions

Deep Motif: Visualizing Genomic Sequence Classifications

Jun 02, 2016
Jack Lanchantin, Ritambhara Singh, Zeming Lin, Yanjun Qi

Figure 1 for Deep Motif: Visualizing Genomic Sequence Classifications

Figure 2 for Deep Motif: Visualizing Genomic Sequence Classifications

Figure 3 for Deep Motif: Visualizing Genomic Sequence Classifications

* 5 pages; 3 figures ; deep learning ; genomic sequence classification; understanding deep models

Access Paper or Ask Questions