no code implementations • COLING (LAW) 2020 • Hung Chau, Saeid Balaneshin, Kai Liu, Ondrej Linda
We evaluate these annotation strategies with respect to their cost and on the task of learning keyphrase extraction models applied with an experimental dataset in the real-estate domain.
no code implementations • 2 May 2024 • Mei Yang, Gao Qiu andJunyong Liu, Kai Liu
This letter proposes a few-shot physics-guided spatial temporal graph convolutional network (FPG-STGCN) to fast solve unit commitment (UC).
no code implementations • 29 Apr 2024 • Bowen Xu, Shaoyu Wu, Kai Liu, Lulu Hu
With the proliferation of large language models (LLMs), the comprehensive alignment of such models across multiple tasks has emerged as a critical area of research.
1 code implementation • 21 Apr 2024 • Kang You, Kai Liu, Li Yu, Pan Gao, Dandan Ding
Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces.
2 code implementations • 12 Apr 2024 • Yanhao Zheng, Kai Liu
Specifically, in the region-proposal stage, proposals that contain novel instances showcase lower objectness scores, since they are treated as background proposals during the training phase.
no code implementations • 10 Apr 2024 • Geyou Zhang, Ce Zhu, Kai Liu
Phase shifting profilometry (PSP) is favored in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise property.
no code implementations • 5 Mar 2024 • Hanlin Tang, Yifu Sun, Decheng Wu, Kai Liu, Jianchen Zhu, Zhanhui Kang
To our best knowledge, we are the first work that achieves almost lossless quantization performance for LLMs under a data-independent setting and our algorithm runs over 10 times faster than the data-dependent methods.
no code implementations • 5 Mar 2024 • Cong Ma, Lei Qiao, Chengkai Zhu, Kai Liu, Zelong Kong, Qing Li, Xueqi Zhou, Yuheng Kan, Wei Wu
Based on HoloVIC, we formulated four tasks to facilitate the development of related research.
no code implementations • 6 Feb 2024 • Chao Chen, Kai Liu, Ze Chen, Yi Gu, Yue Wu, Mingyuan Tao, Zhihang Fu, Jieping Ye
Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs.
no code implementations • NeurIPS 2023 • Chao Chen, Zhihang Fu, Kai Liu, Ze Chen, Mingyuan Tao, Jieping Ye
Most existing OOD detection methods focused on exploring advanced training skills or training-free tricks to prevent the model from yielding overconfident confidence score for unknown samples.
no code implementations • 26 Nov 2023 • Hai Zhu, Yuankai Guo, Ronggang Dou, Kai Liu
Query-LIFE utilizes a query-based multimodal fusion to effectively incorporate the image and title based on the product types.
no code implementations • 17 Nov 2023 • Geyou Zhang, Ce Zhu, Kai Liu, Yipeng Liu
On 3D imaging, light field cameras typically are of single shot, and however, they heavily suffer from low spatial resolution and depth accuracy.
no code implementations • 1 Nov 2023 • Wenyang Hu, Kai Liu, Libin Liu, Huiliang Shang
Human pose assessment and correction play a crucial role in applications across various fields, including computer vision, robotics, sports analysis, healthcare, and entertainment.
no code implementations • 24 Oct 2023 • Yun Li, Lin Niu, Xipeng Zhang, Kai Liu, Jianchen Zhu, Zhanhui Kang
Traditional pruning methods are known to be challenging to work in Large Language Models (LLMs) for Generative AI because of their unaffordable training process and large computational demands.
no code implementations • 2 Oct 2023 • Jianan Zhao, Le Zhuo, Yikang Shen, Meng Qu, Kai Liu, Michael Bronstein, Zhaocheng Zhu, Jian Tang
Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language.
no code implementations • 12 Sep 2023 • Mengyuan Zhang, Kai Liu
Sparse logistic regression is for classification and feature selection simultaneously.
1 code implementation • ICCV 2023 • Kai Liu, Sheng Jin, Zhihang Fu, Ze Chen, Rongxin Jiang, Jieping Ye
The resulting accurate pseudo-tracklets boost learning the feature consistency.
no code implementations • 4 Jul 2023 • Mengyuan Zhang, Kai Liu
We study a class of non-convex and non-smooth problems with \textit{rank} regularization to promote sparsity in optimal solution.
no code implementations • 29 Apr 2023 • Mei Yang, Gao Qiu, Yong Wu, Junyong Liu, Nina Dai, Yue Shui, Kai Liu, Lijie Ding
The increasing scale of alternating current and direct current (AC/DC) hybrid systems necessitates a faster power flow analysis tool than ever.
no code implementations • 18 Apr 2023 • Leida Zhang, Zhengda Lu, Kai Liu, Yiqun Wang
We then propose to alternately optimize the implicit function and the registration between the implicit function and point cloud.
no code implementations • 23 Mar 2023 • Kai Liu, Hailiang Xiong, Gangqiang Yang, Zhengfeng Du, Yewen Cao, Danyal Shah
On the other hand, we need to reduce the dimension of each subspace to keep the size of the overall feature space unchanged when we increase the number of heads, which will significantly weaken the ability to represent the feature of each subspace.
no code implementations • 9 Mar 2023 • Kai Liu, Ziqing Du, Xucheng Wan, Huan Zhou
To mitigate the imperative SC issue, we reformulate the training objective and propose two novel loss schemes that explore the metric of reconstruction improvement performance defined at small chunk-level and leverage the metric associated distribution information.
no code implementations • 7 Mar 2023 • Kai Liu, Yarui Cao
Recent technology and equipment advancements provide with us opportunities to better analyze Alzheimer's disease (AD), where we could collect and employ the data from different image and genetic modalities that may potentially enhance the predictive performance.
no code implementations • 25 Jan 2023 • Xiao Li, Zhihui Zhu, Qiuwei Li, Kai Liu
The symmetric Nonnegative Matrix Factorization (NMF), a special but important class of the general NMF, has found numerous applications in data analysis such as various clustering tasks.
no code implementations • 16 Jan 2023 • Kai Liu, Xucheng Wan, Ziqing Du, Huan Zhou
As a practical alternative of speech separation, target speaker extraction (TSE) aims to extract the speech from the desired speaker using additional speaker cue extracted from the speaker.
1 code implementation • 7 Jan 2023 • Hu Ding, Ruomin Huang, Kai Liu, Haikuo Yu, Zixiu Wang
Though a number of methods have been developed in the past decades, it is still quite challenging to design quality guaranteed algorithm with low complexity for this problem.
1 code implementation • 6 Jan 2023 • Lin Qiu, Aminollah Khormali, Kai Liu
The integration of multi-modal data, such as pathological images and genomic data, is essential for understanding cancer heterogeneity and complexity for personalized treatments, as well as for enhancing survival predictions.
no code implementations • 4 Jan 2023 • Mengyuan Zhang, Kai Liu
Multi-task learning aims to boost the generalization performance of multiple related tasks simultaneously by leveraging information contained in those tasks.
no code implementations • 7 Oct 2022 • Dike Sun, Kai Liu, ShengKai Yang
Capturing the evolving trends of user interest is important for both recommendation systems and advertising systems, and user behavior sequences have been successfully used in Click-Through-Rate(CTR) prediction problems.
no code implementations • 26 Sep 2022 • Kai Liu, Lei Gao, Ling Guan
In this paper, a GPU-based accelerated algorithm is proposed to further optimize the DDCCANet algorithm.
no code implementations • 24 Sep 2022 • Ziqing Du, Kai Liu, Xucheng Wan, Huan Zhou
Overlapped speech detection (OSD) is critical for speech applications in scenario of multi-party conversion.
no code implementations • 24 Sep 2022 • Xucheng Wan, Kai Liu, Ziqing Du, Huan Zhou
To validate the effectiveness of our proposed model, extensive experiments are conducted on the DNS2020 dataset.
1 code implementation • 6 Sep 2022 • Mengyuan Zhang, Kai Liu
Nonnegative matrix factorization (NMF) is widely used for clustering with strong interpretability.
no code implementations • 7 Aug 2022 • Kai Liu, Tianxian Zhang, Lingjiang Kong
In this paper, we first demonstrate the flaw of Weighted QMIX using an ordinary One-Step Matrix Game (OMG), that no matter how the weight is chosen, Weighted QMIX struggles to deal with non-monotonic value decomposition problems with a large variance of reward distributions.
no code implementations • 1 Jul 2022 • Jiamin Liang, Xin Yang, Yuhao Huang, Kai Liu, Xinrui Zhou, Xindi Hu, Zehui Lin, Huanjia Luo, Yuanji Zhang, Yi Xiong, Dong Ni
First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection.
no code implementations • 4 Jun 2022 • Endai Huang, Axiu Mao, Junhui Hou, Yongjian Wu, Weitao Xu, Maria Camila Ceballos, Thomas D. Parsons, Kai Liu
Specifically, CClusnet-Inseg uses each pixel to predict object centers and trace these centers to form masks based on clustering results, which consists of a network for segmentation and center offset vector map, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Centers-to-Mask (C2M), and Remain-Centers-to-Mask (RC2M) algorithms.
no code implementations • 21 May 2022 • Mengyuan Zhang, Kai Liu
To address the above issues, in this paper we propose a novel Enriched Robust Multi-View Kernel Subspace Clustering framework where the consensus affinity matrix is learned from both multi-view data and spectral clustering.
no code implementations • 25 Mar 2022 • Hanlin Tang, Xipeng Zhang, Kai Liu, Jianchen Zhu, Zhanhui Kang
In this work, we propose MKQ-BERT, which further improves the compression level and uses 4-bits for quantization.
no code implementations • 19 Mar 2022 • Kai Liu, Zhiju Chen, Toshiyuki Yamamoto, Liheng Tuo
A convolutional, long short-term memory model combined with a hexagonal convolution operation (H-ConvLSTM) is proposed to explore the complex spatial and temporal relations.
no code implementations • 12 Mar 2022 • Fusen Wang, Kai Liu, Fei Long, Nong Sang, Xiaofeng Xia, Jun Sang
However, the transformer directly partitions the crowd images into a series of tokens, which may not be a good choice due to each pedestrian being an independent individual, and the parameter number of the network is very large.
no code implementations • 8 Mar 2022 • Kai Liu, Tianyi Wu, Cong Liu, Guodong Guo
To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window.
no code implementations • 29 Nov 2021 • Kai Liu
However, most of the studies aim to minimize the loss by measuring the Euclidean distance, though in some fields, angle distance is known to be more important and critical for analysis.
no code implementations • 23 Nov 2021 • Kai Liu, Yarui Cao
In this paper we propose a novel optimization framework to systematically solve robust PCA problem with rigorous theoretical guarantee, based on which we investigate very computationally economic updating algorithms.
no code implementations • 1 Jul 2021 • Kai Liu, Yuyang Zhao, Gang Wang, Bei Peng
Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning.
no code implementations • 14 Mar 2021 • Kai Liu, Yongjian Zhao, Hua Wang
Over the past decade, learning a dictionary from input images for sparse modeling has been one of the topics which receive most research attention in image processing and compressed sensing.
no code implementations • 25 Nov 2020 • Linhao Luo, Liqi Yang, Ju Xin, Yixiang Fang, Xiaofeng Zhang, Xiaofei Yang, Kai Chen, Zhiyuan Zhang, Kai Liu
In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.
1 code implementation • NAACL 2021 • Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, daxiang dong, Hua Wu, Haifeng Wang
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers.
Ranked #4 on Passage Retrieval on Natural Questions
9 code implementations • Interspeech2020 2020 • Geng Yang, Shan Yang, Kai Liu, Peng Fang, Wei Chen, Lei Xie
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
no code implementations • 12 Nov 2019 • Zhiyuan Liu, Huazheng Wang, Fan Shen, Kai Liu, Lijun Chen
We study incentivized exploration for the multi-armed bandit (MAB) problem where the players receive compensation for exploring arms other than the greedy choice and may provide biased feedback on reward.
1 code implementation • 9 Jul 2019 • Qilei Li, Zhen Li, Lu Lu, Gwanggil Jeon, Kai Liu, Xiaomin Yang
The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era.
Ranked #18 on Image Super-Resolution on BSD100 - 4x upscaling
1 code implementation • ACL 2019 • An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li
In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC.
1 code implementation • 16 Mar 2019 • Kai Liu, Qiuwei Li, Hua Wang, Gongguo Tang
However, most of the studies on PCA aim to minimize the loss after projection, which usually measures the Euclidean distance, though in some fields, angle distance is known to be more important and critical for analysis.
no code implementations • 15 Nov 2018 • Sheng Xu, Jian-Feng Zhang, Yi-Yan Wang, Lin-Lin Sun, Huan Wang, Yuan Su, Xiao-Yan Wang, Kai Liu, Tian-Long Xia
An electron-type quasi-2D Fermi surface is found by the angle-dependent Shubnikov-de Haas oscillations, de Haas-van Alphen oscillations and the first-principles calculations.
Materials Science Mesoscale and Nanoscale Physics
no code implementations • NeurIPS 2018 • Zhihui Zhu, Xiao Li, Kai Liu, Qiuwei Li
Symmetric nonnegative matrix factorization (NMF), a special but important class of the general NMF, is demonstrated to be useful for data analysis and in particular for various clustering tasks.
1 code implementation • 11 Nov 2018 • Feng Xue, Xiangnan He, Xiang Wang, Jiandong Xu, Kai Liu, Richang Hong
In this work, we propose a more expressive ICF solution by accounting for the nonlinear and higher-order relationship among items.
no code implementations • WS 2018 • An Yang, Kai Liu, Jing Liu, Yajuan Lyu, Sujian Li
Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between the candidate and reference answers, such as ROUGE and BLEU.
no code implementations • CVPR 2018 • Kai Liu, Hua Wang, Feiping Nie, Hao Zhang
To tackle these two challenges, in this paper we propose a novel image representation learning method that can integrate the local patches (the instances) of an input image (the bag) and its holistic representation into one single-vector representation.
no code implementations • ACL 2018 • Yizhong Wang, Kai Liu, Jing Liu, wei he, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang
Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine.
Ranked #3 on Question Answering on MS MARCO
1 code implementation • 21 Apr 2018 • Jianhua Yang, Kai Liu, Xiangui Kang, Edward K. Wong, Yun-Qing Shi
The architecture contain three component modules: a generator, an embedding simulator and a discriminator.
Multimedia
3 code implementations • WS 2018 • Wei He, Kai Liu, Jing Liu, Yajuan Lyu, Shiqi Zhao, Xinyan Xiao, Yu-An Liu, Yizhong Wang, Hua Wu, Qiaoqiao She, Xuan Liu, Tian Wu, Haifeng Wang
Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.
no code implementations • 8 Jun 2017 • Daniel L. Lau, Yu Zhang, Kai Liu
In the case of phase measuring profilometry (PMP), the projected patterns are composed of a rolling sinusoidal wave, but as a set of time-multiplexed patterns, PMP requires the target surface to remain motionless or for scanning to be performed at such high rates that any movement is small.
3 code implementations • 18 Apr 2017 • Kun Gai, Xiaoqiang Zhu, Han Li, Kai Liu, Zhe Wang
CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.
no code implementations • 14 Jan 2017 • Wenwen Ding, Kai Liu
Therefore, an action can be represented as a subspace corresponding to a point on a Grassmann manifold.