ServiceNow AI Research

1

Equivariant Adaptation of Large Pre-Trained Models
Equivariant Adaptation of Large Pre-Trained Models
Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to …
Conference on Neural Information Processing Systems (NeurIPS),  2023.
Paper Cite
Group Robust Classification Without Any Group Information
Group Robust Classification Without Any Group Information
Empirical risk minimization (ERM) is sensitive to spurious correlations present in training data, which poses a significant risk when …
Conference on Neural Information Processing Systems (NeurIPS),  2023.
Paper Cite Code
Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence
Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence
Block coordinate descent (BCD) methods are widely used for large-scale numerical optimization because of their cheap iteration costs, …
International Conference on Machine Learning (ICML),  2023.
Paper Cite Code
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but …
International Conference on Machine Learning (ICML),  2023.
Paper Cite Code
Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
Multivariate probabilistic time series forecasts are commonly evaluated via proper scoring rules, i.e., functions that are minimal in …
International Conference on Machine Learning (ICML),  2023.
Paper Cite Code Slides Video
Affinity Learning With Blind-spot Self-supervision for Image Denoising
Affinity Learning With Blind-spot Self-supervision for Image Denoising
In this paper, we extend the blind-spot based self-supervised denoising by using affinity learning to remove noise from affected …
International Conference on Acoustics, Speech and Signal Processing (ICASSP),  2023.
Paper 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 …
Conference on Machine Learning and Systems (MLSYS),  2023.
Paper Cite
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. …
European Chapter of the Association for Computational Linguistics (EACL),  2023.
Paper Cite
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
We introduce the StatCan Dialogue Dataset consisting of 4967 conversations between agents working at Statistics Canada and online users …
European Chapter of the Association for Computational Linguistics (EACL),  2023.
Paper 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 …
International Conference of Learning Representations (ICLR),  2023.
Paper Cite Code