565 citations · 851 across the 15 of their papers we have counts for
15 papers
On Hate Scaling Laws For Data-Swamps
Abeba Birhane, Vinay Prabhu, Sang Han +1
`Scale the model, scale the data, scale the GPU-farms' is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann +122
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained…
Multimodal datasets: misogyny, pornography, and malignant stereotypes
Abeba Birhane, Vinay Uday Prabhu, Emmanuel Kahembwe
We have now entered the era of trillion parameter machine learning models trained on billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has giv…
Afro-MNIST: Synthetic generation of MNIST-style datasets for low-resource languages
Daniel J Wu, Andrew C Yang, Vinay U Prabhu
We present Afro-MNIST, a set of synthetic MNIST-style datasets for four orthographies used in Afro-Asiatic and Niger-Congo languages: Ge`ez (Ethiopic), Vai, Osmanya, and N'Ko. Thes…
Large image datasets: A pyrrhic win for computer vision?
Vinay Uday Prabhu, Abeba Birhane
In this paper we investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as s…
Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker
Nicholas Roberts, Vinay Uday Prabhu, Matthew McAteer
This paper explores the scenarios under which an attacker can claim that 'Noise and access to the softmax layer of the model is all you need' to steal the weights of a convolutiona…
Deep Connectomics Networks: Neural Network Architectures Inspired by Neuronal Networks
Nicholas Roberts, Dian Ang Yap, Vinay Uday Prabhu
The interplay between inter-neuronal network topology and cognition has been studied deeply by connectomics researchers and network scientists, which is crucial towards understandi…
Grassmannian Packings in Neural Networks: Learning with Maximal Subspace Packings for Diversity and Anti-Sparsity
Dian Ang Yap, Nicholas Roberts, Vinay Uday Prabhu
Kernel sparsity ("dying ReLUs") and lack of diversity are commonly observed in CNN kernels, which decreases model capacity. Drawing inspiration from information theory and wireless…
Kannada-MNIST: A new handwritten digits dataset for the Kannada language
Vinay Uday Prabhu
In this paper, we disseminate a new handwritten digits-dataset, termed Kannada-MNIST, for the Kannada script, that can potentially serve as a direct drop-in replacement for the ori…
Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance
Vinay Uday Prabhu, Dian Ang Yap, Alexander Wang +1
Attribute prior avoidance entails subconscious or willful non-modeling of (meta)attributes that datasets are oft born with, such as the 40 semantic facial attributes associated wit…
Understanding Adversarial Robustness Through Loss Landscape Geometries
Vinay Uday Prabhu, Dian Ang Yap, Joyce Xu +1
The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surfa…
Fonts-2-Handwriting: A Seed-Augment-Train framework for universal digit classification
Vinay Uday Prabhu, Sanghyun Han, Dian Ang Yap +3
In this paper, we propose a Seed-Augment-Train/Transfer (SAT) framework that contains a synthetic seed image dataset generation procedure for languages with different numeral syste…
On Lyapunov exponents and adversarial perturbation
Vinay Uday Prabhu, Nishant Desai, John Whaley
In this paper, we would like to disseminate a serendipitous discovery involving Lyapunov exponents of a 1-D time series and their use in serving as a filtering defense tool against…
Latent Sentiment Detection in Online Social Networks: A Communications-oriented View
Rohit Negi, Vinay Uday Prabhu, Miguel Rodrigues
In this paper, we consider the problem of latent sentiment detection in Online Social Networks such as Twitter. We demonstrate the benefits of using the underlying social network a…