Research Area
Year Published

626 Results

October 30, 2018

Scaling Neural Machine Translation

Conference on Machine Translation (WMT)

Sequence to sequence learning models still require several days to reach state of the art performance on large benchmark datasets using a single machine. This paper shows that reduced precision and large batch training can speedup training by nearly 5x on a single 8- GPU machine with careful tuning and implementation.

By: Myle Ott, Sergey Edunov, David Grangier, Michael Auli
October 29, 2018

XNLI: Evaluating Cross-lingual Sentence Representations

Empirical Methods in Natural Language Processing (EMNLP)

In this work, we construct an evaluation set for XLU by extending the development and test sets of the Multi-Genre Natural Language Inference Corpus (MultiNLI) to 15 languages, including low-resource languages such as Swahili and Urdu.

By: Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel R. Bowman, Holger Schwenk, Ves Stoyanov
October 26, 2018

SING: Symbol-to-Instrument Neural Generator

Conference on Neural Information Processing Systems (NIPS)

In this work, we study the more computationally efficient alternative of generating the waveform frame-by-frame with large strides. We present SING, a lightweight neural audio synthesizer for the original task of generating musical notes given desired instrument, pitch and velocity.

By: Alexandre Défossez, Neil Zeghidour, Nicolas Usunier, Leon Bottou, Francis Bach
October 25, 2018

Peri-personal space as a prior in coupling visual and proprioceptive signals

Scientific Reports 2018

It has been suggested that the integration of multiple body-related sources of information within the peri-personal space (PPS) scaffolds body ownership. However, a normative computational framework detailing the functional role of PPS is still missing. Here we cast PPS as a visuo-proprioceptive Bayesian inference problem whereby objects we see in our environment are more likely to engender sensations as they come near to the body. We propose that PPS is the refection of such an increased a priori probability of visuo-proprioceptive coupling that surrounds the body.

By: Jean-Paul Noel, Majed Samad, Andrew Doxon, Justin Clark, Sean Keller, Massimiliano Di Luca
Areas: AR/VR
October 15, 2018

On Ends-to-Ends Encryption: Asynchronous Group Messaging with Strong Security Guarantees

ACM Conference on Computer and Communications Security (CCS)

We show for the first time that post-compromise security can be achieved in realistic, asynchronous group messaging systems. We present a design called Asynchronous Ratcheting Trees (ART), which uses tree-based Diffie-Hellman key exchange to allow a group of users to derive a shared symmetric key even if no two are ever online at the same time.

By: Katriel Cohn-Gordon, Cas Cremers, Luke Garratt, Jon Millican, Kevin Milner
October 12, 2018

Conveying Language through Haptics: A Multi-sensory Approach

International Symposium on Wearable Computers 2018

We propose using a multi-sensory haptic device called MISSIVE, which can be worn on the upper arm and is capable of producing brief cues, sufficient in quantity to encode the full English phoneme set.

By: Nathan Dunkelberger, Jenny Sullivan, Joshua Bradley, Nickolas P Walling, Indu Manickam, Gautam Dasarathy, Ali Israr, Frances Lau, Keith Klumb, Brian Knott, Freddy Abnousi, Richard Baraniuk, Marcia K. O’Malley
October 1, 2018

The effects of natural scene statistics on text readability in additive displays

Human Factors and Ergonomics Society

The minimum contrast needed for optimal text readability with additive displays (e.g. AR devices) will depend on the spatial structure of the background and text. Natural scenes and text follow similar spectral patterns. Therefore, natural scenes can mask low contrast text – making it difficult to read. In a set of experiments, we determine the minimum viable contrast for readability on an additive display.

By: Daryn R. Blanc-Goldhammer, Kevin J. MacKenzie
Areas: AR/VR