ServiceNow AI Research

9

Surrogate Minimization: An Optimization Algorithm for Training Large Neural Networks with Model Parallelism
Surrogate Minimization: An Optimization Algorithm for Training Large Neural Networks with Model Parallelism
Optimizing large memory-intensive neural networks requires distributing its layers across multiple GPUs (referred to as model …
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
Paper Cite
The Unsolved Challenges of LLMs in Open-Ended Web Tasks: A Case Study
The Unsolved Challenges of LLMs in Open-Ended Web Tasks: A Case Study
In this work, we investigate the challenges associated with developing goal-driven AI agents capable of performing open-ended tasks in …
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
Paper Cite Video
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
The accurate modeling of dynamics in interactive environments is critical for suc- cessful long-range prediction. Such a capability …
European Workshop on Reinforcement Learning (EWRL),  2023.
Paper Cite
Invariant Causal Set Covering Machines
Invariant Causal Set Covering Machines
Rule-based models, such as decision trees, appeal to practitioners due to their interpretable nature. However, the learning algorithms …
Workshop on Spurious Correlations, Invariance, and Stability (ICML),  2023.
Paper Cite Code
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
The practical utility of causality in decision-making is widely recognized, with causal discovery and inference being inherently …
Workshop on Structured Probabilistic Inference & Generative Modeling (ICML),  2023.
Paper Cite
Causal Discovery with Language Models as Imperfect Experts
Causal Discovery with Language Models as Imperfect Experts
Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, …
Workshop on Structured Probabilistic Inference & Generative Modeling (ICML),  2023.
Paper Cite Code Slides Video
Explaining Graph Neural Networks Using Interpretable Local Surrogates
Explaining Graph Neural Networks Using Interpretable Local Surrogates
We propose an interpretable local surrogate (ILS) method for understanding the predictions of black-box graph models. Explainability …
Workshop at the International Conference on Machine Learning (ICML),  2023.
Paper Cite
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
Imagination is a crucial aspect of human intelligence that enables us to combine concepts in novel ways and make sense of new …
Workshop at the International Conference on Machine Learning (ICML),  2023.
Paper Cite
Workflow discovery in low data regimes
Workflow discovery in low data regimes
Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can …
Workshop at the International Conference on Machine Learning (ICML),  2023.
Paper Cite
Multilingual Code Retrieval Without Paired Data: A New Benchmark and Experiments
Multilingual Code Retrieval Without Paired Data: A New Benchmark and Experiments
We seek to overcome limitations to code retrieval quality posed by the scarcity of data containing pairs of code snippets and natural …
Workshop at the International Conference on Learning Representations (ICLR),  2023.
Paper Cite Slides Video