A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Kavli Affiliate: Xiang Zhang | First 5 Authors: Puyuan Liu, Xiang Zhang, Lili Mou, , | Summary: Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE […]


Continue.. A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Kavli Affiliate: Xiang Zhang | First 5 Authors: Puyuan Liu, Xiang Zhang, Lili Mou, , | Summary: Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE […]


Continue.. A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Unifying model for three forms of contextual modulation including feedback input from higher visual areas

Kavli Affiliate: Kenneth Miller | Authors: Serena Di santo, Mario Dipoppa, Andreas Keller, Morgane Roth, Massimo Scanziani and Kenneth D Miller | Summary: Neural responses to a localized visual stimulus are modulated by the content of its surrounding. This phenomenon manifests in several forms of contextual modulation, including three interrelated properties of the visual cortex: […]


Continue.. Unifying model for three forms of contextual modulation including feedback input from higher visual areas

Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Kavli Affiliate: Zheng Zhu | First 5 Authors: Jianfei Yang, Xiangyu Peng, Kai Wang, Zheng Zhu, Jiashi Feng | Summary: Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain. It does not require access to both the source-domain […]


Continue.. Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Study of Time Evolution of Thermal and Non-Thermal Emission from an M-Class Solar Flare

Kavli Affiliate: Tadayuki Takahashi | First 5 Authors: Shunsaku Nagasawa, Tomoko Kawate, Noriyuki Narukage, Tadayuki Takahashi, Amir Caspi | Summary: We conduct a wide-band X-ray spectral analysis in the energy range of 1.5-100 keV to study the time evolution of the M7.6 class flare of 2016 July 23, with the Miniature X-ray Solar Spectrometer (MinXSS) […]


Continue.. Study of Time Evolution of Thermal and Non-Thermal Emission from an M-Class Solar Flare