66 citations · 101 across the 16 of their papers we have counts for
16 papers
Adaptive Adversarial Training Does Not Increase Recourse Costs
Ian Hardy, Jayanth Yetukuri, Yang Liu
Recent work has connected adversarial attack methods and algorithmic recourse methods: both seek minimal changes to an input instance which alter a model's classification decision.…
Machine Learning for Infectious Disease Risk Prediction: A Survey
Mutong Liu, Yang Liu, Jiming Liu
Infectious diseases, either emerging or long-lasting, place numerous people at risk and bring heavy public health burdens worldwide. In the process against infectious diseases, pre…
Towards Understanding the Capability of Large Language Models on Code Clone Detection: A Survey
Shihan Dou, Junjie Shan, Haoxiang Jia +7
Code cloning, the duplication of code fragments, is common in software development. While some reuse aids productivity, excessive cloning hurts maintainability and introduces bugs.…
ZeroFlow: Scalable Scene Flow via Distillation
Kyle Vedder, Neehar Peri, Nathaniel Chodosh +6
Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimizatio…
Decadal Temperature Prediction via Chaotic Behavior Tracking
Jinfu Ren, Yang Liu, Jiming Liu
Decadal temperature prediction provides crucial information for quantifying the expected effects of future climate changes and thus informs strategic planning and decision-making i…
Adversarial Contrastive Distillation with Adaptive Denoising
Yuzheng Wang, Zhaoyu Chen, Dingkang Yang +4
Adversarial Robustness Distillation (ARD) is a novel method to boost the robustness of small models. Unlike general adversarial training, its robust knowledge transfer can be less…
Entropy-bounded solutions to the Cauchy problem of compressible planar non-resistive magnetohydrodynamics equations with far field vacuum
Jinkai Li, Mingjie Li, Yang Liu +1
We investigate the Cauchy problem to the compressible planar non-resistive magnetohydrodynamic equations with zero heat conduction. The global existence of strong solutions to such…
Modeling and Performance Analysis of Single-Server Database Over Quasi-static Rayleigh Fading Channel
Mengying Chen, Wannian An, Yang Liu +4
Cloud database is the key technology in cloud computing. The effective and efficient service quality of the cloud database is inseparable from communication technology, just as imp…
Long-range spin-orbital order in the spin-orbital SU(2)SU(2)U(1) model
Yang Liu, Z. Y. Xie, Hong-Gang Luo +1
By using the tensor-network state algorithm, we study a spin-orbital model with SU(2)SU(2)U(1) symmetry on the triangular lattice. This model was proposed to descri…
Soft Augmentation for Image Classification
Yang Liu, Shen Yan, Laura Leal-Taixé +2
Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. Th…
Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization
Hengrui Luo, Younghyun Cho, James W. Demmel +2
This paper presents a new type of hybrid model for Bayesian optimization (BO) adept at managing mixed variables, encompassing both quantitative (continuous and integer) and qualita…
Entropy-bounded solutions to the 3D compressible heat-conducting magnetohydrodynamic equations with vacuum at infinity
Yang Liu, Xin Zhong
The mathematical analysis on the behavior of the entropy for viscous, compressible, and heat conducting magnetohydrodynamic flows near the vacuum region is a challenging problem as…
Global existence of strong solutions with large oscillations and vacuum to the compressible nematic liquid crystal flows in 3D bounded domains
Yang Liu, Xin Zhong
We investigate compressible nematic liquid crystal flows in three-dimensional (3D) bounded domains with slip boundary condition for velocity and Neumann boundary condition for orie…
Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
Shaopeng Fu, Fengxiang He, Yang Liu +2
The tremendous amount of accessible data in cyberspace face the risk of being unauthorized used for training deep learning models. To address this concern, methods are proposed to…
Deep learning based track reconstruction on CEPC luminometer
Liu Yang, Hao Cai, Kai Zhu
We study the track reconstruction algorithms of the CEPC luminometer. Depend on the current geometry design, the conventional track reconstruction method is applied, but it suffers…
Field-free spin-orbit torque switching from geometrical domain wall pinning
Jong Min Lee, Kaiming Cai, Guang Yang +4
Spin-orbit torques, which utilize spin currents arising from the spin-orbit coupling, offer a novel method to electrically switch the magnetization with perpendicular anisotropy. H…