ServiceNow AI Research

1

Typing assumptions improve identification in causal discovery - theory and algorithms
Typing assumptions improve identification in causal discovery - theory and algorithms
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an …
Causal Learning and Reasoning (CLeaR),  2022.
Paper Cite Code
VIM: Variational Independent Modules for Video Prediction
VIM: Variational Independent Modules for Video Prediction
We introduce a variational inference model called VIM, for Variational Independent Modules, for sequential data that learns and infers …
Causal Learning and Reasoning (CLeaR),  2022.
Paper Cite
Continual Learning via Local Module Composition
Continual Learning via Local Module Composition
Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
Paper Cite
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
Paper Cite Code
Systematic Generalization with Edge Transformers
Systematic Generalization with Edge Transformers
Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
Paper Cite
The Dynamics of Functional Diversity throughout Neural Network Training
The Dynamics of Functional Diversity throughout Neural Network Training
Deep ensembles offer consistent performance gains, both in terms of reduced generalization error and improved predictive uncertainty …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
Paper Cite
Towards Neural Functional Program Evaluation
Towards Neural Functional Program Evaluation
This paper explores the capabilities of current transformer-based language models for program evaluation of simple functional …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
Paper Cite
Picard: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
Picard: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of …
Conference on Empirical Methods in Natural Language Processing (EMNLP),  2021.
Paper Cite Code Video
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Explainability for machine learning models has gained considerable attention within the research community given the importance of …
International Conference on Computer Vision (ICCV),  2021.
Paper Cite Code
Generative Compositional Augmentations for Scene Graph Prediction
Generative Compositional Augmentations for Scene Graph Prediction
Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection …
International Conference on Computer Vision (ICCV),  2021.
Paper Cite