Search Results for author: Ting Wu

Found 15 papers, 7 papers with code

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

1 code implementation18 Jun 2024 Zhen Huang, Zengzhi Wang, Shijie Xia, Xuefeng Li, Haoyang Zou, Ruijie Xu, Run-Ze Fan, Lyumanshan Ye, Ethan Chern, Yixin Ye, Yikai Zhang, Yuqing Yang, Ting Wu, Binjie Wang, Shichao Sun, Yang Xiao, Yiyuan Li, Fan Zhou, Steffi Chern, Yiwei Qin, Yan Ma, Jiadi Su, Yixiu Liu, Yuxiang Zheng, Shaoting Zhang, Dahua Lin, Yu Qiao, PengFei Liu

We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions.

Scale-Invariant Feature Disentanglement via Adversarial Learning for UAV-based Object Detection

no code implementations24 May 2024 Fan Liu, Liang Yao, Chuanyi Zhang, Ting Wu, Xinlei Zhang, Xiruo Jiang, Jun Zhou

Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features.

Disentanglement object-detection +1

Refining Segmentation On-the-Fly: An Interactive Framework for Point Cloud Semantic Segmentation

no code implementations11 Mar 2024 Peng Zhang, Ting Wu, Jinsheng Sun, Weiqing Li, Zhiyong Su

This paper concentrates on an unexplored yet meaningful task, i. e., interactive point cloud semantic segmentation, which assigns high-quality semantic labels to all points in a scene with user corrective clicks.

Point Cloud Segmentation Segmentation +1

Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization

1 code implementation20 May 2023 Ting Wu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization.

Out-of-Distribution Generalization text-classification +1

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.

Decoder 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.

Cloud Computing

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 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.