1 code implementation • 20 Sep 2023 • Haoyu Wang, Guozheng Ma, Cong Yu, Ning Gui, Linrui Zhang, Zhiqi Huang, Suwei Ma, Yongzhe Chang, Sen Zhang, Li Shen, Xueqian Wang, Peilin Zhao, DaCheng Tao
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
no code implementations • 26 Dec 2022 • Cong Yu, Dongheng Zhang, Zhi Wu, Zhi Lu, Chunyang Xie, Yang Hu, Yan Chen
Different from existing methods that predict human poses from RF signals on the signal level directly, we consider the structure difference between the RF signals and the human poses, propose to transform the RF signals to the pose domain on the feature level based on Optimal Transport (OT) theory, and generate human poses from the transformed features.
no code implementations • 3 Nov 2022 • Junru Wu, Yi Liang, Feng Han, Hassan Akbari, Zhangyang Wang, Cong Yu
For example, even in the commonly adopted instructional videos, a speaker can sometimes refer to something that is not visually present in the current frame; and the semantic misalignment would only be more unpredictable for the raw videos from the internet.
no code implementations • 22 May 2022 • Jiaxin Huang, Tianqi Liu, Jialu Liu, Adam D. Lelkes, Cong Yu, Jiawei Han
Multi-Task Learning (MTL) models have shown their robustness, effectiveness, and efficiency for transferring learned knowledge across tasks.
no code implementations • 9 Mar 2022 • Donghui Hu, Yu Zhang, Cong Yu, Jian Wang, Yaofei Wang
Image steganography is the art and science of using images as cover for covert communications.
no code implementations • 25 Jan 2022 • Zhi Wu, Dongheng Zhang, Chunyang Xie, Cong Yu, Jinbo Chen, Yang Hu, Yan Chen
To overcome such limitations, in this paper, we propose to utilize the radio signals, which can traverse obstacles and are unaffected by the lighting conditions to achieve silhouette segmentation.
no code implementations • 7 Dec 2021 • Cong Yu, Zhi Wu, Dongheng Zhang, Zhi Lu, Yang Hu, Yan Chen
To the best of our knowledge, this is the first work to generate optical images based on RF signals.
1 code implementation • EMNLP 2021 • Xiang Deng, Yu Su, Alyssa Lees, You Wu, Cong Yu, Huan Sun
We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts.
Ranked #1 on Semantic Parsing on GraphQuestions
2 code implementations • ICLR 2022 • Yi Tay, Vinh Q. Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, Donald Metzler
In this paper, we propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model.
Ranked #3 on Paraphrase Identification on Quora Question Pairs
no code implementations • Findings (ACL) 2021 • Richard Yuanzhe Pang, Adam D. Lelkes, Vinh Q. Tran, Cong Yu
Given the lack of existing datasets, we create a dataset for AgreeSum, and provide annotations on article-summary entailment relations for a subset of the clusters in the dataset.
no code implementations • 1 Jun 2021 • Jialu Liu, Tianqi Liu, Cong Yu
Effectively modeling text-rich fresh content such as news articles at document-level is a challenging problem.
no code implementations • Findings (ACL) 2021 • Jiaming Shen, Jialu Liu, Tianqi Liu, Cong Yu, Jiawei Han
In this study, we present a new text encoder pre-training method that improves ELECTRA based on multi-task learning.
1 code implementation • 18 Feb 2021 • Adam D. Lelkes, Vinh Q. Tran, Cong Yu
As a first step towards measuring news informedness at a scale, we study the problem of quiz-style multiple-choice question generation, which may be used to survey users about their knowledge of recent news.
no code implementations • 1 Aug 2020 • Tao Cai, Cong Yu, Xing Wei
Two configurations have been considered: waves propagate from the convective layer to the radiative stratified stable layer, or In this paper, we study inertial and gravity wave transmissions near radiative-convective boundaries on the {\it f}-plane.
Fluid Dynamics Solar and Stellar Astrophysics
1 code implementation • 26 Jun 2020 • Xiang Deng, Huan Sun, Alyssa Lees, You Wu, Cong Yu
In this paper, we present TURL, a novel framework that introduces the pre-training/fine-tuning paradigm to relational Web tables.
Ranked #1 on Column Type Annotation on WikipediaGS-CTA
no code implementations • WS 2020 • Anjalie Field, Sascha Rothe, Simon Baumgartner, Cong Yu, Abe Ittycheriah
We evaluate the performance of transformer encoders with various decoders for information organization through a new task: generation of section headings for Wikipedia articles.
3 code implementations • COLING 2020 • Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks.
2 code implementations • 26 Jan 2020 • Xiaotao Gu, Yuning Mao, Jiawei Han, Jialu Liu, Hongkun Yu, You Wu, Cong Yu, Daniel Finnie, Jiaqi Zhai, Nicholas Zukoski
In this work, we study the problem of generating representative headlines for news stories.
3 code implementations • 13 Jan 2020 • Liang Xu, Yu tong, Qianqian Dong, Yixuan Liao, Cong Yu, Yin Tian, Weitang Liu, Lu Li, Caiquan Liu, Xuanwei Zhang
In this paper, we introduce the NER dataset from CLUE organization (CLUENER2020), a well-defined fine-grained dataset for named entity recognition in Chinese.
Chinese Named Entity Recognition named-entity-recognition +2
no code implementations • ICCV 2019 • Cong Yu, Yang Hu, Yan Chen, Bing Zeng
Fashion recommendation is the task of suggesting a fashion item that fits well with a given item.
no code implementations • 30 Jun 2018 • Braden Hancock, Hongrae Lee, Cong Yu
This is accomplished by extracting many text snippets that have potentially relevant information to the table, encoding them into an input sequence, and using both copy and generation mechanisms in the decoder to balance relevance and readability of the generated title.
1 code implementation • 21 Feb 2018 • Jingbo Shang, Tianhang Sun, Jiaming Shen, Xingbang Liu, Anja Gruenheid, Flip Korn, Adam Lelkes, Cong Yu, Jiawei Han
We build Maester based on the following two key observations: (1) relatedness can commonly be determined by keywords and entities occurring in both questions and articles, and (2) the level of agreement between the investigative question and the related news article can often be decided by a few key sentences.