ServiceNow AI Research

9

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on …
Workshop at the International Conference of Learning Representation (ICLR),  2024.
PDF Cite Video
Towards Disentangled High-level Causal Explanations in Text
In this work, we propose a causal representation learning framework for learning disentangled and intervenable high-level explanations …
Mid-Atlantic Student Colloquium on Speech, Language and Learning,  2024.
Cite
A Sparsity Principle for Partially Observable Causal
A Sparsity Principle for Partially Observable Causal
Causal representation learning (CRL) aims at identifying high-level causal variables from low-level data, e.g. images. Current methods …
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
Capture the Flag: Uncovering Data Insights with Large Language Models
Capture the Flag: Uncovering Data Insights with Large Language Models
The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making. …
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
Lag-Llama: A Foundation Model for Probabilistic Time Series Forecasting
Lag-Llama: A Foundation Model for Probabilistic Time Series Forecasting
In this work, we present Lag-Llama, a general-purpose probabilistic time series forecasting model trained on a large collection of time …
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
Multi-View Causal Representation Learning with Partial Observability
Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as …
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
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.
PDF 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.
PDF 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.
PDF 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.
PDF Cite