Chang Xu

TL;DR: This paper investigates the geometric properties of a user's rating vector, and designs a matrix completion method on the simplex that efficiently optimized the resulting objective function by a Riemannian conjugate gradient method.

TL;DR: This paper identifies two major types of stance expressions that are linguistically distinct, and proposes a tailored dual-view adaptation network (DAN) to adapt these expressions across domains and finds that the learned view features can be more easily aligned and more stance-discriminative in either or both views, leading to more transferable overall features after combining the views.

TL;DR: This paper proposes to automatically generate textual password mnemonics, i.e., natural language sentences, which are intended to help users better memorize passwords, and introduces \textit{DeepMnemonic}, a deep attentive encoder-decoder framework which takes a password as input and then automatically generates a mnemonic sentence for the password.

TL;DR: Results demonstrated that DHW-221, as a novel P-gp inhibitor, represents a prospective therapeutic candidate to overcome MDR in Taxol-resistant NSCLC treatment.

TL;DR: This paper upgrades the classical weight functions by considering instance complexities, which are described by the distances between instance features and their corresponding labels, and demonstrates the significance of investigating both the dynamic and static complexities of multi-label examples.