activity
20172021
most citedMobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU

10 citations · 22 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CL20213 cited

IrEne: Interpretable Energy Prediction for Transformers

Qingqing Cao, Yash Kumar Lal, Harsh Trivedi +2

Existing software-based energy measurements of NLP models are not accurate because they do not consider the complex interactions between energy consumption and model execution. We…

cs.IR2020

Bew: Towards Answering Business-Entity-Related Web Questions

Qingqing Cao, Oriana Riva, Aruna Balasubramanian +1

We present BewQA, a system specifically designed to answer a class of questions that we call Bew questions. Bew questions are related to businesses/services such as restaurants, ho…

cs.CL2020

Towards Accurate and Reliable Energy Measurement of NLP Models

Qingqing Cao, Aruna Balasubramanian, Niranjan Balasubramanian

Accurate and reliable measurement of energy consumption is critical for making well-informed design choices when choosing and training large scale NLP models. In this work, we show…

cs.CL20209 cited

DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering

Qingqing Cao, Harsh Trivedi, Aruna Balasubramanian +1

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It…

cs.DC201710 cited

MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU

Qingqing Cao, Niranjan Balasubramanian, Aruna Balasubramanian

In this paper, we explore optimizations to run Recurrent Neural Network (RNN) models locally on mobile devices. RNN models are widely used for Natural Language Processing, Machine…