activity
20172021
most citedLong Range Arena: A Benchmark for Efficient Transformers

195 citations · 206 across the 8 of their papers we have counts for

collaborators

8 papers

cs.AI2021

The Threat of Offensive AI to Organizations

Yisroel Mirsky, Ambra Demontis, Jaidip Kotak +7

AI has provided us with the ability to automate tasks, extract information from vast amounts of data, and synthesize media that is nearly indistinguishable from the real thing. How…

cs.LG2020★ 195 cited

Long Range Arena: A Benchmark for Efficient Transformers

Yi Tay, Mostafa Dehghani, Samira Abnar +7

Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transf…

cs.CV2020★ 1 cited

SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space

Liu Yang

In this work, we formulate a visual dialog as an information flow in which each piece of information is encoded with the joint visual-linguistic representation of a single dialog r…

cs.DS2019★ 1 cited

Computing and Testing Small Connectivity in Near-Linear Time and Queries via Fast Local Cut Algorithms

Sebastian Forster, Danupon Nanongkai, Thatchaphol Saranurak +2

Consider the following "local" cut-detection problem in a directed graph: We are given a seed vertex and need to remove at most edges so that at most edges can be reach…

cs.DS2019★ 5 cited

A Faster Local Algorithm for Detecting Bounded-Size Cuts with Applications to Higher-Connectivity Problems

Sebastian Forster, Liu Yang

Consider the following "local" cut-detection problem in a directed graph: We are given a starting vertex and need to detect whether there is a cut with at most edges crossi…

cs.CL2019★ 4 cited

Contextual Aware Joint Probability Model Towards Question Answering System

Liu Yang, Lijing Song

In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embedd…