Search Results for author: Ting Wu

Found 10 papers, 4 papers with code

Less is Better: Recovering Intended-Feature Subspace to Robustify NLU Models

1 code implementation COLING 2022 Ting Wu, Tao Gui

When delving into a lower manifold to remove redundancies, RISK reveals that an extremely low-dimensional subspace with intended features can robustly represent the highly biased dataset.

Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective

2 code implementations COLING 2022 Shihan Dou, Rui Zheng, Ting Wu, Songyang Gao, Junjie Shan, Qi Zhang, Yueming Wu, Xuanjing Huang

Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).

Fact Verification Natural Language Inference +1

GANet: Glyph-Attention Network for Few-Shot Font Generation

no code implementations29 Sep 2021 Mingtao Guo, Wei Xiong, Zheng Wang, Yong Tang, Ting Wu

Font generation is a valuable but challenging task, it is time consuming and costly to design font libraries which cover all glyphs with various styles.

Font Generation

A Wideband Sliding Correlation Channel Sounder in 65 nm CMOS: Evaluation Board Performance

no code implementations12 Jun 2021 Dipankar Shakya, Ting Wu, Michael E. Knox, Theodore S. Rappaport

This paper presents a compact sliding correlation-based channel sounder baseband built on a monolithic integrated circuit (IC) using 65 nm CMOS, implemented as an evaluation board achieving a 2 GHz RF bandwidth.

A Wideband Sliding Correlator based Channel Sounder in 65 nm CMOS: An Evaluation Board Design

no code implementations28 Sep 2020 Dipankar Shakya, Ting Wu, Theodore S. Rappaport

Wide swaths of bandwidth at millimeter-wave (mmWave) and Terahertz (THz) frequencies stimulate diverse applications in wireless sensing, imaging, position location, cloud computing, and much more.

DeepTFP: Mobile Time Series Data Analytics based Traffic Flow Prediction

1 code implementation1 Oct 2017 Yuanfang Chen, Falin Chen, Yizhi Ren, Ting Wu, Ye Yao

However, as the mobile data of vehicles has been widely collected by sensor-embedded devices in transportation systems, it is possible to predict the traffic flow by analysing mobile data.

Time Series Prediction

The Human Body and Millimeter-Wave Wireless Communication Systems: Interactions and Implications

1 code implementation19 Mar 2015 Ting Wu, Theodore S. Rappaport, Christopher M. Collins

With increasing interest in millimeter wave wireless communications, investigations on interactions between the human body and millimeter wave devices are becoming important.

Emerging Technologies

The Extended UCB Policies for Frequentist Multi-armed Bandit Problems

no code implementations8 Dec 2011 Keqin Liu, Haoran Chen, Weibing Deng, Ting Wu

The multi-armed bandit (MAB) problem is a widely studied model in the field of reinforcement learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.