Niranjani Prasad — accepted AI-conference papers

2026

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar

ICLR 2026poster

Masked diffusion models (MDMs) offer a compelling alternative to autoregres- sive models (ARMs) for discrete text generation because they enable parallel token sampling, rather than sequential, left-to-right generation. This means po- tentially much faster inference. However, effective parallel samp…

Cited by 0 Source ↗Scholar ↗

2015

Scaling recurrent neural network language models

Will Williams, Niranjani Prasad, David Mrva, Tom Ash, Tony Robinson

ICASSP 2015accepted

This paper investigates the scaling properties of Recurrent Neural Network Language Models (RNNLMs). We discuss how to train very large RNNs on GPUs and address the questions of how RNNLMs scale with respect to model size, training-set size, computational costs and memory. Our analysis shows that de…

Cited by 0 Source ↗Scholar ↗