Health-related acoustic signals, such as cough and breathing sounds, are...
For safety, AI systems in health undergo thorough evaluations before
dep...
We present Face0, a novel way to instantaneously condition a text-to-ima...
AI models have shown promise in many medical imaging tasks. However, our...
Cardiovascular diseases (CVDs) are responsible for a large proportion of...
Text-driven image and video diffusion models have recently achieved
unpr...
Large language models (LLMs) have demonstrated impressive capabilities i...
Inference from large autoregressive models like Transformers is slow -
d...
We present UniTune, a simple and novel method for general text-driven im...
Despite recent advances in natural language understanding and generation...
External eye photos were recently shown to reveal signs of diabetic reti...
Grounded text generation systems often generate text that contains factu...
The operational flood forecasting system by Google was developed to prov...
In this paper, we introduce adversarially robust streaming algorithms fo...
Background: Floods are the most common natural disaster in the world,
af...
Floods are among the most common and deadly natural disasters in the wor...
A streaming algorithm is said to be adversarially robust if its accuracy...
Colorectal Cancer (CRC) is a global health problem, resulting in 900K de...
Multitask learning, i.e. taking advantage of the relatedness of individu...
Automatic speech recognition (ASR) systems have dramatically improved ov...
Named Entity Recognition (NER) has been mostly studied in the context of...
We present differentially private efficient algorithms for learning unio...
Effective riverine flood forecasting at scale is hindered by a multitude...
Learning hydrologic models for accurate riverine flood prediction at sca...
Metric embeddings are immensely useful representation of interacting ent...