335 citations · 752 across the 15 of their papers we have counts for
15 papers
Augmentations vs Algorithms: What Works in Self-Supervised Learning
Warren Morningstar, Alex Bijamov, Chris Duvarney +8
We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL). While the recent literature in this space le…
A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Stephen R. Pfohl, Heather Cole-Lewis, Rory Sayres +27
Large language models (LLMs) hold promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evalua…
Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations
Neha Kalibhat, Warren Morningstar, Alex Bijamov +3
Self-Supervised Learning (SSL) enables training performant models using limited labeled data. One of the pillars underlying vision SSL is the use of data augmentations/perturbation…
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer
Renan A. Rojas-Gomez, Karan Singhal, Ali Etemad +3
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with…
Random Field Augmentations for Self-Supervised Representation Learning
Philip Andrew Mansfield, Arash Afkanpour, Warren Richard Morningstar +1
Self-supervised representation learning is heavily dependent on data augmentations to specify the invariances encoded in representations. Previous work has shown that applying dive…
Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout
Pengfei Guo, Warren Richard Morningstar, Raviteja Vemulapalli +3
Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessib…
Towards Generalist Biomedical AI
Tao Tu, Shekoofeh Azizi, Danny Driess +29
Medicine is inherently multimodal, with rich data modalities spanning text, imaging, genomics, and more. Generalist biomedical artificial intelligence (AI) systems that flexibly en…
Federated Variational Inference: Towards Improved Personalization and Generalization
Elahe Vedadi, Joshua V. Dillon, Philip Andrew Mansfield +3
Conventional federated learning algorithms train a single global model by leveraging all participating clients' data. However, due to heterogeneity in client generative distributio…
Towards Expert-Level Medical Question Answering with Large Language Models
Karan Singhal, Tao Tu, Juraj Gottweis +28
Recent artificial intelligence (AI) systems have reached milestones in "grand challenges" ranging from Go to protein-folding. The capability to retrieve medical knowledge, reason o…
Large Language Models Encode Clinical Knowledge
Karan Singhal, Shekoofeh Azizi, Tao Tu +27
Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications i…
Federated Training of Dual Encoding Models on Small Non-IID Client Datasets
Raviteja Vemulapalli, Warren Richard Morningstar, Philip Andrew Mansfield +4
Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of e…
Camera View Adjustment Prediction for Improving Image Composition
Yu-Chuan Su, Raviteja Vemulapalli, Ben Weiss +4
Image composition plays an important role in the quality of a photo. However, not every camera user possesses the knowledge and expertise required for capturing well-composed photo…
Contrastive Learning for Label-Efficient Semantic Segmentation
Xiangyun Zhao, Raviteja Vemulapalli, Philip Mansfield +4
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Netwo…
Links: A High-Dimensional Online Clustering Method
Philip Andrew Mansfield, Quan Wang, Carlton Downey +2
We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space. The algorithm is appropriate when it is nec…
Speaker Diarization with LSTM
Quan Wang, Carlton Downey, Li Wan +2
For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications. However, mirroring the rise of d…