ICML 2018

Hierarchical Text Generation and Planning for Strategic Dialogue

ICML 2018 facebookresearch/end-to-end-negotiator

End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors.

DECISION MAKING TEXT GENERATION

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

ICML 2018 deepmind/scalable_agent

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.

ATARI GAMES

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

ICML 2018 anishathalye/obfuscated-gradients

We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

Provable defenses against adversarial examples via the convex outer adversarial polytope

ICML 2018 locuslab/convex_adversarial

We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training data.

ADVERSARIAL ATTACK

Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron

ICML 2018 syang1993/gst-tacotron

We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody.

SPEECH SYNTHESIS

Autoregressive Convolutional Neural Networks for Asynchronous Time Series

ICML 2018 mbinkowski/nntimeseries

We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series.

TIME SERIES

Junction Tree Variational Autoencoder for Molecular Graph Generation

ICML 2018 wengong-jin/icml18-jtnn

We evaluate our model on multiple tasks ranging from molecular generation to optimization.

DRUG DISCOVERY

Gated Path Planning Networks

ICML 2018 lileee/gated-path-planning-networks

Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture.