523 citations · 1.4k across the 23 of their papers we have counts for
26 papers
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
Shraman Pramanick, Rama Chellappa, Subhashini Venugopalan
Seeking answers to questions within long scientific research articles is a crucial area of study that aids readers in quickly addressing their inquiries. However, existing question…
A Design Space for Intelligent and Interactive Writing Assistants
Mina Lee, Katy Ilonka Gero, John Joon Young Chung +33
In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to addr…
Parameter Efficient Tuning Allows Scalable Personalization of LLMs for Text Entry: A Case Study on Abbreviation Expansion
Katrin Tomanek, Shanqing Cai, Subhashini Venugopalan
Abbreviation expansion is a strategy used to speed up communication by limiting the amount of typing and using a language model to suggest expansions. Here we look at personalizing…
Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings
Joel Shor, Ruyue Agnes Bi, Subhashini Venugopalan +3
Automatic Speech Recognition (ASR) in medical contexts has the potential to save time, cut costs, increase report accuracy, and reduce physician burnout. However, the healthcare in…
Assessing ASR Model Quality on Disordered Speech using BERTScore
Jimmy Tobin, Qisheng Li, Subhashini Venugopalan +3
Word Error Rate (WER) is the primary metric used to assess automatic speech recognition (ASR) model quality. It has been shown that ASR models tend to have much higher WER on speak…
Is Attention All That NeRF Needs?
Mukund Varma T, Peihao Wang, Xuxi Chen +3
We present Generalizable NeRF Transformer (GNT), a transformer-based architecture that reconstructs Neural Radiance Fields (NeRFs) and learns to renders novel views on the fly from…
Context-Aware Abbreviation Expansion Using Large Language Models
Shanqing Cai, Subhashini Venugopalan, Katrin Tomanek +3
Motivated by the need for accelerating text entry in augmentative and alternative communication (AAC) for people with severe motor impairments, we propose a paradigm in which phras…
TRILLsson: Distilled Universal Paralinguistic Speech Representations
Joel Shor, Subhashini Venugopalan
Recent advances in self-supervision have dramatically improved the quality of speech representations. However, deployment of state-of-the-art embedding models on devices has been r…
Using a Cross-Task Grid of Linear Probes to Interpret CNN Model Predictions On Retinal Images
Katy Blumer, Subhashini Venugopalan, Michael P. Brenner +1
We analyze a dataset of retinal images using linear probes: linear regression models trained on some "target" task, using embeddings from a deep convolutional (CNN) model trained o…
Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases
Subhashini Venugopalan, Joel Shor, Manoj Plakal +4
Automatic classification of disordered speech can provide an objective tool for identifying the presence and severity of speech impairment. Classification approaches can also help…
Guided Integrated Gradients: An Adaptive Path Method for Removing Noise
Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci +3
Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy p…
Predicting Risk of Developing Diabetic Retinopathy using Deep Learning
Ashish Bora, Siva Balasubramanian, Boris Babenko +13
Diabetic retinopathy (DR) screening is instrumental in preventing blindness, but faces a scaling challenge as the number of diabetic patients rises. Risk stratification for the dev…
Scientific Discovery by Generating Counterfactuals using Image Translation
Arunachalam Narayanaswamy, Subhashini Venugopalan, Dale R. Webster +10
Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation tech…
Scaling Symbolic Methods using Gradients for Neural Model Explanation
Subham Sekhar Sahoo, Subhashini Venugopalan, Li Li +2
Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly li…
Attribution in Scale and Space
Shawn Xu, Subhashini Venugopalan, Mukund Sundararajan
We study the attribution problem [28] for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of…
It's easy to fool yourself: Case studies on identifying bias and confounding in bio-medical datasets
Subhashini Venugopalan, Arunachalam Narayanaswamy, Samuel Yang +10
Confounding variables are a well known source of nuisance in biomedical studies. They present an even greater challenge when we combine them with black-box machine learning techniq…
Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning
Avinash Varadarajan, Pinal Bavishi, Paisan Raumviboonsuk +15
Diabetic eye disease is one of the fastest growing causes of preventable blindness. With the advent of anti-VEGF (vascular endothelial growth factor) therapies, it has become incre…
Detecting Cancer Metastases on Gigapixel Pathology Images
Yun Liu, Krishna Gadepalli, Mohammad Norouzi +10
Each year, the treatment decisions for more than 230,000 breast cancer patients in the U.S. hinge on whether the cancer has metastasized away from the breast. Metastasis detection…
Utilizing Large Scale Vision and Text Datasets for Image Segmentation from Referring Expressions
Ronghang Hu, Marcus Rohrbach, Subhashini Venugopalan +1
Image segmentation from referring expressions is a joint vision and language modeling task, where the input is an image and a textual expression describing a particular region in t…
Captioning Images with Diverse Objects
Subhashini Venugopalan, Lisa Anne Hendricks, Marcus Rohrbach +3
Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual…
Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text
Subhashini Venugopalan, Lisa Anne Hendricks, Raymond Mooney +1
This paper investigates how linguistic knowledge mined from large text corpora can aid the generation of natural language descriptions of videos. Specifically, we integrate both a…
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
Lisa Anne Hendricks, Subhashini Venugopalan, Marcus Rohrbach +3
While recent deep neural network models have achieved promising results on the image captioning task, they rely largely on the availability of corpora with paired image and sentenc…
A Multi-scale Multiple Instance Video Description Network
Huijuan Xu, Subhashini Venugopalan, Vasili Ramanishka +2
Generating natural language descriptions for in-the-wild videos is a challenging task. Most state-of-the-art methods for solving this problem borrow existing deep convolutional neu…
Sequence to Sequence -- Video to Text
Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue +3
Real-world videos often have complex dynamics; and methods for generating open-domain video descriptions should be sensitive to temporal structure and allow both input (sequence of…