ServiceNow AI Research

Computer Vision

GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
While numerous recent benchmarks focus on evaluating generic Vision-Language Models (VLMs), they fall short in addressing the unique …
International Conference on Computer Vision (ICCV),  2025.
PDF Cite Code
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding …
International Conference of Learning Representations (ICLR),  2025.
PDF Cite Code Video
Deep Learning in Ultrasound localization Microscopy: Applications and perspectives
Deep Learning in Ultrasound localization Microscopy: Applications and perspectives
Ultrasound Localization Microscopy (ULM) is a novel super-resolution imaging technique that can image the vasculature in vivo at depth …
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (IEEE TUFFC),  2025.
PDF Cite
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Ultrasound Localization Microscopy (ULM) is a non-invasive technique that allows for the imaging of micro-vessels in vivo, at depth and …
IEEE Transactions on Image Processing (IEEE TIP),  2025.
PDF Cite
VCR: Visual Caption Restoration
VCR: Visual Caption Restoration
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially …
Workshop at the Neural Information Processing Systems (NeurIPS),  2024.
PDF Cite Code
Few-shot Learning for Sign Language Recognition with Embedding Propagation
Few-shot Learning for Sign Language Recognition with Embedding Propagation
Sign language is a primary channel for the deaf and hard-hearing to communicate. Sign language consists of many signs with different …
ArXiv,  2024.
PDF Cite
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
Multimodal multihop question answering is a complex task that requires reasoning over multiple sources of information, such as images …
ArXiv,  2024.
PDF Cite Code Video
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
Ultrasound Localization Microscopy (ULM) is a non-invasive technique that allows for the imaging of micro-vessels in vivo, at depth and …
ArXiv,  2024.
PDF Cite Code
StarVector: Generating Scalable Vector Graphics Code from Images and Text
StarVector: Generating Scalable Vector Graphics Code from Images and Text
Scalable Vector Graphics (SVGs) have become integral in modern image rendering and graphic design applications due to their infinite …
ArXiv,  2024.
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