1

Deep Extrapolation for Attribute-Enhanced Generation
TL;DR: How do we generate sequences that extrapolate beyond the training distribution?
Abstract: Attribute extrapolation in sample …
<strong>Alvin Chan</strong>*, Ali Madani*, Ben Krause, Nikhil Naik
PDF Cite Code
Self-Instantiated Recurrent Units with Dynamic Soft Recursion
TL;DR: We propose the self-instantiated recurrent unit that is characterized by recursive instantiation of the model itself, where the …
Aston Zhang, Yi Tay, Yikang Shen, <strong>Alvin Chan</strong>*, Shuai Zhang
PDF Cite
On Orthogonality Constraints for Transformers
TL;DR: Orthogonality constraints the encourages numerical stability improves model’s performance in NLP tasks.
Abstract: …
Aston Zhang, <strong>Alvin Chan</strong>*, Yi Tay, Jie Fu, Shuohang Wang, Shuai Zhang, Huajie Shao, Shuochao Yao, Roy Ka-Wei Lee
Cite
CoCon: A Self-Supervised Approach for Controlled Text Generation
TL;DR: We propose CoCon to control the content of text generation from LMs by conditioning on content inputs at an interleave layer. …
<strong>Alvin Chan</strong>*, Yew-Soon Ong, Bill Pung, Aston Zhang, Jie Fu
PDF Cite Code Video
Parameterization of Hypercomplex Multiplications
TL;DR: We propose a new parameterization of hypercomplex multiplications for architectural flexibility and effectiveness.
Abstract: …
Aston Zhang, Yi Tay, Shuai Zhang, <strong>Alvin Chan</strong>*, Anh Tuan Luu, Siu Cheung Hui, Jie Fu
PDF Cite
RNA Alternative Splicing Prediction with Discrete Compositional Energy Network
TL;DR: We construct an RNA alternative splicing regression dataset (CAPD) and propose DCEN to predict splicing outcomes by modeling …
<strong>Alvin Chan</strong>*, Anna Korsakova*, Yew-Soon Ong, Fernaldo Richtia Winnerdy, Kah Wai Lim, Anh Tuan Phan
PDF Cite Code Video
Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder
TL;DR: We propose Conditional Adversarially Regularized Autoencoder to imbue poison signature and generate natural-looking poisoned …
<strong>Alvin Chan</strong>*, Tay Yi, Yew-Soon Ong, Aston Zhang
PDF Cite Code Video
What it Thinks is Important is Important: Robustness Transfers through Input Gradients
TL;DR: By regularizing for similar input gradients, we can transfer adversarial robustness from a teacher to a student classifier even …
<strong>Alvin Chan</strong>*, Yi Tay, Yew-Soon Ong
PDF Cite Code Video
Jacobian Adversarially Regularized Networks for Robustness
TL;DR: We show that training classifiers to produce salient input Jacobian matrices with a GAN-like regularization can boost …
<strong>Alvin Chan</strong>*, Yi Tay, Yew-Soon Ong, Jie Fu
PDF Cite Code Video