ServiceNow AI Research

9

Attention for Compositional Modularity
Attention for Compositional Modularity
Modularity and compositionality are promising inductive biases for addressing longstanding problems in machine learning such as better …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite Video
A General Purpose Neural Architecture for Geospatial Systems
A General Purpose Neural Architecture for Geospatial Systems
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Breadth-First Pipeline Parallelism
Breadth-First Pipeline Parallelism
We introduce Breadth-First Pipeline Parallelism, a novel training schedule which optimizes the combination of pipeline and data …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Can large language models build causal graphs?
Can large language models build causal graphs? 
Building causal graphs can be a laborious process. To ensure all relevant causal pathways have been captured, researchers often have to …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Choreographer: Learning and Adapting Skills in Imagination
Choreographer: Learning and Adapting Skills in Imagination
Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Constraining Low-level Representations to Define Effective Confidence Scores
Constraining Low-level Representations to Define Effective Confidence Scores
Neural networks are known to fail with high confidence, especially for data that somehow differs from the training distribution. Such …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite Video
Contrastive Self-supervision Defines General-Purpose Similarity Functions
Contrastive Self-supervision Defines General-Purpose Similarity Functions
Handling out-of-distribution (OOD) and adversarial inputs has become a major stake in the real-world deployment of machine learning …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Exploring the Design Space of Generative Diffusion Processes for Sparse Graphs
Exploring the Design Space of Generative Diffusion Processes for Sparse Graphs
We extend score-based generative diffusion processes (GDPs) to sparse graphs and other inherently discrete data, with a focus on …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Implicit Offline Reinforcement Learning via Supervised Learning
Implicit Offline Reinforcement Learning via Supervised Learning
Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset of …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite
Learning Discrete Directed Acyclic Graphs via Backpropagation
Learning Discrete Directed Acyclic Graphs via Backpropagation
Recently continuous relaxations have been proposed in order to learn directed acyclic graphs (DAGs) by backpropagation, instead of …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite