ServiceNow Research

Multi-modal Learning

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.
PDF Cite
Haptics-based Curiosity for Sparse-reward Tasks
Haptics-based Curiosity for Sparse-reward Tasks
Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks …
Conference on Robot Learning (CoRL),  2022.
PDF Cite Code
Adaptive Cross-Modal Few-shot Learning
Adaptive Cross-Modal Few-shot Learning
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to …
Conference on Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite Code
Neural Multisensory Scene Inference
Neural Multisensory Scene Inference
For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine …
Conference on Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite Code
Integrating Vision and Language in Social Networks for Identifying Visual Patterns of Personality Traits
Integrating Vision and Language in Social Networks for Identifying Visual Patterns of Personality Traits
International Journal of Social Science and Humanity,  2019.
PDF Cite
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and …
International Conference on Learning Representations (ICLR),  2019.
PDF Cite Code