ServiceNow AI Research

Domain Adaptation

Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a …
Oleksiy Ostapenko, Charles Guille-Escuret, Luke Kumar, Max Tian, Denis Kocetkov, Gopeshh Subbaraj, Raymond Li, Joel Lamy Poirier, Sébastien Paquet, Torsten Scholak
Conference on Language Modeling Workshops,  2025.
Paper Cite
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
We introduce AgentAda, the first LLM-powered analytics agent that can learn and use new analytics skills to extract more specialized …
Amirhossein Abaskohi, Amrutha Ramesh, Shailesh Nanisetty, Chirag Goel, David Vazquez, Christopher Pal, Spandana Gella, Giuseppe Carenini, Issam H. Laradji
Workshop at the Annual Meeting of the Association for Computational Linguistics (ACL),  2025.
Paper Cite
Scaling up ML-based Black-box Planning with Partial STRIPS Models
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
Matias Greco, Alvaro Torralba, Jorge Baier, Hector Palacios
Workshop at International Join Conference on Artificial Intelligence (IJCAI),  2022.
Paper Cite Code
Scaling up ML-based Black-box Planning with Partial STRIPS Models
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
Matias Greco, Alvaro Torralba, Jorge Baier, Hector Palacios
ICAPS'22 Workshop on Reliable Data-Driven Planning and Scheduling,  2022.
Paper Cite Code
Active Domain Randomization
Active Domain Randomization
Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is …
Bhairav Mehta, Manfred Diaz, Florian Golemo, Christopher Pal, Liam Paull
Conference on Robot Learning (CoRL),  2019.
Paper Cite Code
Domain-Adaptive Single-view 3D Reconstruction
Domain-Adaptive Single-view 3D Reconstruction
Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very …
Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn
International Conference on Computer Vision (ICCV),  2019.
Paper Cite Code
Unsupervised Domain Adaptation with Similarity Learning
Unsupervised Domain Adaptation with Similarity Learning
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an …
Pedro O. Pinheiro
Computer Vision and Pattern Recognition (CVPR),  2018.
Paper Cite