ServiceNow AI Research

1

Context-Aware Visual Compatibility Prediction
Context-Aware Visual Compatibility Prediction
How do we determine whether two or more clothing items are compatible or visually appealing? Part of the answer lies in understanding …
Computer Vision and Pattern Recognition (CVPR),  2019.
PDF Cite
Hierarchical Importance Weighted Autoencoders
Hierarchical Importance Weighted Autoencoders
Importance weighted variational inference (Burda et al., 2015) uses multiple i.i.d. samples to have a tighter variational lower bound. …
International Conference on Machine Learning (ICML),  2019.
PDF Cite
Investigating Trust Factors in Human-Robot Shared Control: Implicit Gender Bias Around Robot Voice
This paper explores the impact of warnings, audio feedback, and gender on human-robot trust in the context of autonomous driving and …
Conference on Computer and Robotic Vision (CRV),  2019.
PDF Cite
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite
Meta-Learning Framework with Applications to Zero-Shot Time Series Forecasting
Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite
On Difficulties of Probability Distillation
On Difficulties of Probability Distillation
Probability distillation has recently been of interest to deep learning practitioners as it presents a practical solution for sampling …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite
Probabilistic Planning with Sequential Monte Carlo Methods
Probabilistic Planning with Sequential Monte Carlo Methods
In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite
Quaternion Recurrent Neural Networks
Quaternion Recurrent Neural Networks
Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite
Systematic Generalization: What Is Required and Can It Be Learned?
Systematic Generalization: What Is Required and Can It Be Learned?
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite
Improving Optimization Bounds using Machine Learning: Decision Diagrams meet Deep Reinforcement Learning
Improving Optimization Bounds using Machine Learning: Decision Diagrams meet Deep Reinforcement Learning
Finding tight bounds on the optimal solution is a critical element of practical solution methods for discrete optimization problems. In …
Association for the Advancement of Artificial Intelligence (AAAI),  2019.
PDF Cite