no code implementations • 27 Mar 2024 • Yuqing Wang, Mika V. Mäntylä, Serge Demeyer, Mutlu Beyazit, Joanna Kisaakye, Jesse Nyyssölä
Within the same MSS, our framework achieves an average accuracy of 93. 26\% and 85. 2\% across 50 meta-testing tasks for Trainticket and OnlineBoutique, respectively, when provided with 10 instances for each task.
1 code implementation • 18 Mar 2024 • Shuang Wang, Fei Deng, Peifan Jiang, Zishan Gong, Xiaolin Wei, Yuqing Wang
In response to this challenge, we propose a novel diffusion model reconstruction framework tailored for 3D seismic data.
no code implementations • 24 Feb 2024 • Haotian Xia, Zhengbang Yang, Yuqing Wang, Rhys Tracy, Yun Zhao, Dongdong Huang, Zezhi Chen, Yan Zhu, Yuan-Fang Wang, Weining Shen
A deep understanding of sports, a field rich in strategic and dynamic content, is crucial for advancing Natural Language Processing (NLP).
no code implementations • 1 Feb 2024 • Yuqing Wang, Malvika Pillai, Yun Zhao, Catherine Curtin, Tina Hernandez-Boussard
In the high-stakes realm of healthcare, ensuring fairness in predictive models is crucial.
1 code implementation • 29 Dec 2023 • Yuqing Wang, Yun Zhao
To address this gap, our study undertakes a thorough evaluation of Gemini's performance in complex reasoning tasks that necessitate the integration of commonsense knowledge across modalities.
no code implementations • 14 Dec 2023 • Yuqing Wang, Zhenyu Weng, Zhaokun Zhou, Shuaijian Ji, Zhongjie Ye, Yuesheng Zhu
Over the past years, Printed Mathematical Expression Recognition (PMER) has progressed rapidly.
1 code implementation • 20 Nov 2023 • Mika Mäntylä, Yuqing Wang, Jesse Nyyssölä
By integrating diverse datasets, log representation methods and anomaly detectors, LogLead facilitates comprehensive benchmarking in log analysis research.
no code implementations • 26 Oct 2023 • Yuqing Wang, Zhenghao Xu, Tuo Zhao, Molei Tao
This regularity, together with gradient descent using a large learning rate that favors flatter regions, results in these nontrivial dynamical behaviors.
no code implementations • 25 Oct 2023 • Yuqing Wang, Prashanth Vijayaraghavan, Ehsan Degan
This study proposes a Prototype-based Multi-view Network (PROMINET) that incorporates semantic and structural information from email data.
1 code implementation • 2 Oct 2023 • Yuqing Wang, Yun Zhao
In this paper, we introduce TRAM, a temporal reasoning benchmark composed of ten datasets, encompassing various temporal aspects of events such as order, arithmetic, frequency, and duration, designed to facilitate a comprehensive evaluation of the temporal reasoning capabilities of large language models (LLMs).
1 code implementation • 26 Sep 2023 • Haotian Xia, Rhys Tracy, Yun Zhao, Yuqing Wang, Yuan-Fang Wang, Weining Shen
Our frameworks combine setting ball trajectory recognition with a novel set trajectory classifier to generate comprehensive and advanced statistical data.
no code implementations • 18 Sep 2023 • Shaofei Huang, Han Li, Yuqing Wang, Hongji Zhu, Jiao Dai, Jizhong Han, Wenge Rong, Si Liu
Explicit object-level semantic correspondence between audio and visual modalities is established by gathering object information from visual features with predefined audio queries.
1 code implementation • 10 Aug 2023 • Yuqing Wang, Yun Zhao
This study underscores the potential to amplify the understanding abilities of LLMs and highlights the benefits of mirroring human introspective reasoning in NLU tasks.
no code implementations • 10 May 2023 • Yuqing Wang, Yun Zhao, Linda Petzold
The Segment Anything Model (SAM) is a foundation model for general image segmentation.
1 code implementation • 9 Apr 2023 • Yuqing Wang, Yun Zhao, Linda Petzold
In this study, we conduct a comprehensive evaluation of state-of-the-art LLMs, namely GPT-3. 5, GPT-4, and Bard, within the realm of clinical language understanding tasks.
1 code implementation • CVPR 2023 • Yuqing Wang, Yizhi Wang, Longhui Yu, Yuesheng Zhu, Zhouhui Lian
First, we adopt Transformers instead of RNNs to process sequential data and design a relaxation representation for vector outlines, markedly improving the model's capability and stability of synthesizing long and complex outlines.
no code implementations • 22 Aug 2022 • Yuqing Wang, Xiangxian Li, Zhuang Qi, Jingyu Li, Xuelong Li, Xiangxu Meng, Lei Meng
Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features.
no code implementations • 26 Jun 2022 • Yuqing Wang, Yun Zhao, Linda Petzold
As critically ill patients frequently develop anemia or coagulopathy, transfusion of blood products is a frequent intervention in the Intensive Care Units (ICU).
1 code implementation • 27 May 2022 • Lingkai Kong, Yuqing Wang, Molei Tao
The problem of optimization on Stiefel manifold, i. e., minimizing functions of (not necessarily square) matrices that satisfy orthogonality constraints, has been extensively studied.
no code implementations • 28 Mar 2022 • Yuqing Wang, Yun Zhao, Linda Petzold
Most current multivariate time series (MTS) classification algorithms focus on improving the predictive accuracy.
no code implementations • 28 Mar 2022 • Yuqing Wang, Yun Zhao, Rachael Callcut, Linda Petzold
In this paper, we propose a multimodal Transformer model for early sepsis prediction, using the physiological time series data and clinical notes for each patient within $36$ hours of ICU admission.
no code implementations • 23 Feb 2022 • Longhui Yu, Zhenyu Weng, Yuqing Wang, Yuesheng Zhu
However, distilling knowledge from two teacher models could result in the student model making some redundant predictions.
no code implementations • ICLR 2022 • Yuqing Wang, Minshuo Chen, Tuo Zhao, Molei Tao
Moreover, we rigorously establish an implicit bias of GD induced by such a large learning rate, termed 'balancing', meaning that magnitudes of $X$ and $Y$ at the limit of GD iterations will be close even if their initialization is significantly unbalanced.
no code implementations • 1 Oct 2021 • Yun Zhao, Yuqing Wang, Junfeng Liu, Haotian Xia, Zhenni Xu, Qinghang Hong, Zhiyang Zhou, Linda Petzold
In this paper, we perform quantitative analysis of COVID-19 forecasting of confirmed cases and deaths across different regions in the United States with different forecasting horizons, and evaluate the relative impacts of the following three dimensions on the predictive performance (improvement and variation) through different evaluation metrics: model selection, hyperparameter tuning, and the length of time series required for training.
8 code implementations • NeurIPS 2021 • Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #48 on Semantic Segmentation on ADE20K val
no code implementations • 19 Mar 2021 • Yuqing Wang, Yun Zhao, Rachael Callcut, Linda Petzold
However, blindly pursuing complex classifiers is unwise as it also brings the risk of greater performance variation.
no code implementations • 19 Mar 2021 • Yun Zhao, Qinghang Hong, Xinlu Zhang, Yu Deng, Yuqing Wang, Linda Petzold
However, there is a lack of deep learning methods that can model the relationship between measurements, clinical notes and mortality outcomes.
no code implementations • NeurIPS 2020 • Kaixuan Huang, Yuqing Wang, Molei Tao, Tuo Zhao
We then compare the kernel of deep ResNets with that of deep FFNets and discover that the class of functions induced by the kernel of FFNets is asymptotically not learnable, as the depth goes to infinity.
2 code implementations • CVPR 2021 • Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen, Baoshan Cheng, Hao Shen, Huaxia Xia
Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
Ranked #33 on Video Instance Segmentation on YouTube-VIS validation
no code implementations • CVPR 2020 • Yuqing Wang, Zhaoliang Xu, Hao Shen, Baoshan Cheng, Lirong Yang
Accordingly, we decompose the instance segmentation into two parallel subtasks: Local Shape prediction that separates instances even in overlapping conditions, and Global Saliency generation that segments the whole image in a pixel-to-pixel manner.
no code implementations • 14 Feb 2020 • Kaixuan Huang, Yuqing Wang, Molei Tao, Tuo Zhao
We then compare the kernel of deep ResNets with that of deep FFNets and discover that the class of functions induced by the kernel of FFNets is asymptotically not learnable, as the depth goes to infinity.