Publications
Our research helps push the boundaries of clinical AI, informing the technology we build while contributing to the advancement of healthcare and machine learning.
Training integrable parameterizations of deep neural networks in the infinite-width limit
Uncertainty-aware automated assessment of the arm impedance with upper-limb exoskeletons
Score-based generative modeling through stochastic differential equations
Aggregating similarity metrics for natural language generation
Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization
TorchKbNufft: A high-level, hardware-agnostic non-uniform fast Fourier transform
fastMRI: An open dataset and benchmarks for accelerated MRI
Using deep learning to accelerate knee MRI at 3 T: results of an interchangeability study
The GraphNet zoo: an all-in-one graph based deep semi-supervised framework for medical image classification
Inferring transmission histories of rare alleles in population-scale genealogies
Multimodal attribute extraction
Learning to speak and act in a fantasy text adventure game
Engaging image captioning via personality
Real-time inference in multi-sentence tasks with deep pretrained transformers
Reference-less quality estimation of text simplification systems
Build it break it fix it for dialogue safety: Robustness from adversarial human attack
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Ringo: Interactive graph analytics on big-memory machines
Poly-encoders: Transformer architectures and pre-training strategies for fast and accurate multi-sentence scoring
Weaver: Deep co-encoding of questions and documents for machine reading
Training millions of personalized dialogue agents
Ready to elevate care?
Ambient AI, dictation, and real-time intelligence - seamlessly integrated to improve clinical workflows.
Learn more
Generating notes
Capturing the visit






