ServiceNow AI Research

1

MAGNIFICO: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations
MAGNIFICO: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations
Humans possess a remarkable ability to assign novel interpretations to linguistic expressions, enabling them to learn new words and …
Conference on Empirical Methods in Natural Language Processing (EMNLP),  2023.
PDF Cite
PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation
PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation
Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training …
Conference on Empirical Methods in Natural Language Processing (EMNLP),  2023.
PDF Cite Video
TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification
TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification
The ability to detect intent in dialogue systems has become increasingly important in modern technology. These systems often generate a …
Conference on Empirical Methods in Natural Language Processing (EMNLP),  2023.
PDF Cite
Are Diffusion Models Vision-And-Language Reasoners?
Are Diffusion Models Vision-And-Language Reasoners?
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, …
Conference on Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
Handling out-of-distribution (OOD) samples has become a major stake in the real-world deploy- ment of machine learning systems. This …
Conference on Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
Egocentric Planning for Scalable Embodied Task Achievement
Egocentric Planning for Scalable Embodied Task Achievement
Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing …
Conference on Neural Information Processing Systems (NeurIPS),  2023.
PDF Cite
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.
PDF 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.
PDF Cite
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.
PDF Cite
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.
PDF Cite