[nmt]

[1] Addressing the rare word problem in neural machine translation(2014). [arxiv] [PPT] [summary] [code] [code] [code]

[2] Neural Machine Translation of Rare Words with Subword Units 2015. [arxiv] [PPT] [code] [code] [code] [code]

[3] Effective approaches to attention-based neural machine translation (2015). [arxiv] [PPT] [PPT] [code] [code] [code] [code] [code] [code] [code] [code]

[4] A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation 2016. [arxiv] [summary] [summary] [code] [code]

[5] Fully Character-Level Neural Machine Translation without Explicit Segmentation 2016. [arxiv] [summary] [code]

[6] Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 2016. [arxiv] (Milestone) [summary] [PPT]

[Sergey Levine from UC Berkeley]

[1] Evolving large-scale neural networks for vision-based reinforcement learning 2013. [pdf] [PPT]

[2] End-to-end training of deep visuomotor policies (2016): 1-40. [pdf] [PPT] [summary] [PPT] [code]

[3] Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours (2015). [arxiv] [PPT]

[4] Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection (2016). [arxiv] [PPT] [iee spectrum news]

[5] Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning (2016). [arxiv] [PPT] [PPT] [code]

[6] Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search (2016). [arxiv]

[7] Deep Reinforcement Learning for Robotic Manipulation (2016). [arxiv]

[8] Sim-to-Real Robot Learning from Pixels with Progressive Nets (2016). [arxiv] [PPT] [PPT] [PPT]

[9] Learning to navigate in complex environments (2016). [arxiv] [code]

[neural style-code] [1] Inceptionism: Going Deeper into Neural Networks. [html] (Deep Dream) [PPT] [PPT] [PPT]

[2] A neural algorithm of artistic style (2015). [arxiv] (Outstanding Work, most successful method currently) [PPT] [PPT] [PPT] [PPT]

[3] Generative Visual Manipulation on the Natural Image Manifold 2016. [arxiv] (iGAN) [PPT] [PPT] [PPT] [PPT] [PPT] [code]

[4] Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks (2016). [arxiv] (Neural Doodle) [PPT] [PPT] [PPT] [[code] [code]

[5] Colorful Image Colorization (2016). [arxiv] [PPT] [PPT] [PPT] [PPT] [PPT] [PPT]

[6] Perceptual losses for real-time style transfer and super-resolution (2016). [arxiv] [PPT] [PPT] [PPT] [PPT] [PPT] [code] [PPT]

[7] A learned representation for artistic style (2016). [arxiv] [PPT] [PPT] [PPT] [PPT] [PPT] [code] [code] [code] [code] [code] [code] [code] [review] [code] [code]

[8] Controlling Perceptual Factors in Neural Style Transfer (2016). [arxiv] (control style transfer over spatial location,colour information and across spatial scale) [code] [code] [code] [code] [code] [code]

[9] Texture Networks: Feed-forward Synthesis of Textures and Stylized Images(2016). [arxiv] (texture generation and style transfer) [PPT] [code]

[1] Fully convolutional networks for semantic segmentation 2015. [arxiv] [PPT] [PPT] [PPT] [PPT] [PPT] [code] [PPT] [code] [code] [code] [code] [code]

[2] Semantic image segmentation with deep convolutional nets and fully connected crfs 2015. [arxiv] [PPT] [code] [code] [code] [code] [code] [code] [code] [code]

[3] Learning to segment object candidates. 2015. [arxiv] [PPT] [code]

[4] Instance-aware semantic segmentation via multi-task network cascades 2016 [arxiv] [PPT] [PPT] [code]

[5] Instance-sensitive Fully Convolutional Networks (2016). [arxiv] [PPT] [PPT] [PPT] [PPT] [code] [code]