activity
20152022
most citedLuna: Linear Unified Nested Attention

49 citations · 120 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20221 cited

Learning Representations Robust to Group Shifts and Adversarial Examples

Ming-Chang Chiu, Xuezhe Ma

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions.…

cs.LG20213 cited

Examining and Combating Spurious Features under Distribution Shift

Chunting Zhou, Xuezhe Ma, Paul Michel +1

A central goal of machine learning is to learn robust representations that capture the causal relationship between inputs features and output labels. However, minimizing empirical…

cs.LG202149 cited

Luna: Linear Unified Nested Attention

Xuezhe Ma, Xiang Kong, Sinong Wang +4

The quadratic computational and memory complexities of the Transformer's attention mechanism have limited its scalability for modeling long sequences. In this paper, we propose Lun…

cs.LG2019

MaCow: Masked Convolutional Generative Flow

Xuezhe Ma, Xiang Kong, Shanghang Zhang +1

Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both trainin…

cs.LG201913 cited

MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

Xuezhe Ma, Chunting Zhou, Eduard Hovy

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretica…

cs.LG2016

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

Xuezhe Ma, Eduard Hovy

State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this pape…