338 citations · 1.1k across the 73 of their papers we have counts for
7 papers · 1 filter
Sentence-State LSTM for Text Representation
Yue Zhang, Qi Liu, Linfeng Song
Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investiga…
Constrained Graph Variational Autoencoders for Molecule Design
Qi Liu, Miltiadis Allamanis, Marc Brockschmidt +1
Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of…
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks
Qi Liu, Tao Liu, Zihao Liu +3
DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example,…
On Modular Training of Neural Acoustics-to-Word Model for LVCSR
Zhehuai Chen, Qi Liu, Hao Li +1
End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which…
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
Zihao Liu, Qi Liu, Tao Liu +4
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recent…
Light Transport Simulation via Generalized Multiple Importance Sampling
Qi Liu, Yiheng Zhang, Lizhuang Ma
Multiple importance sampling (MIS) is employed to reduce variance of estimators, but when sampling and weighting are not suitable to the integrand, the estimators would have extra…
Divide and Recombine for Large and Complex Data: Model Likelihood Functions using MCMC
Qi Liu, Anindya Bhadra, William S. Cleveland
In Divide & Recombine (D&R), big data are divided into subsets, each analytic method is applied to subsets, and the outputs are recombined. This enables deep analysis and practical…