1 code implementation • Findings (NAACL) 2022 • Jin Qian, Bowei Zou, Mengxing Dong, Xiao Li, AiTi Aw, Yu Hong
Conversational Question Answering (ConvQA) is required to answer the current question, conditioned on the observable paragraph-level context and conversation history.
no code implementations • 1 May 2024 • Xiao Li, Qian Gong, Jaemoon Lee, Scott Klasky, Anand Rangarajan, Sanjay Ranka
Scientists conduct large-scale simulations to compute derived quantities-of-interest (QoI) from primary data.
no code implementations • 30 Apr 2024 • Xin Ma, Puchen Zhu, Xiao Li, Xiaoyin Zheng, Jianshu Zhou, Xuchen Wang, Kwok Wai Samuel Au
In this work, we propose a minimal set of parameters based depth-dependent distortion model (MDM), which considers the radial and decentering distortions of the lens to improve the accuracy of stereo vision systems and simplify their calibration process.
no code implementations • 28 Apr 2024 • Jaemoon Lee, Ki Sung Jung, Qian Gong, Xiao Li, Scott Klasky, Jacqueline Chen, Anand Rangarajan, Sanjay Ranka
We present an approach called guaranteed block autoencoder that leverages Tensor Correlations (GBATC) for reducing the spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications.
no code implementations • 18 Apr 2024 • Peiwen Jiang, Chao-Kai Wen, Xiao Li, Shi Jin, Geoffrey Ye Li
Considering the high speed of satellites, an adaptive encoder-decoder is proposed to protect important features and avoid frequent retransmissions.
1 code implementation • 17 Apr 2024 • Xiao Li, Yong Jiang, Shen Huang, Pengjun Xie, Gong Cheng, Fei Huang
Our objective is to train a generative model that can simultaneously provide a score indicating the presence of shared key point between a pair of arguments and generate the shared key point.
1 code implementation • 3 Apr 2024 • Qijun Luo, Hengxu Yu, Xiao Li
This work presents BAdam, an optimizer that leverages the block coordinate optimization framework with Adam as the inner solver.
no code implementations • 22 Mar 2024 • Xiao Li, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky
In the scenario of Adaptive Cruise Control (ACC), we employ the Deep Ensemble to estimate distance headway to the lead vehicle from RGB images and enable the downstream controller to account for the estimation uncertainty.
no code implementations • 4 Mar 2024 • Li Sun, Mengjie Li, Yong Yang, Xiao Li, Lin Liu, Pengfei Zhang, Haohua Du
Annotating anchor users is laborious and expensive, and thus it is impractical to work with quantities of anchor users.
1 code implementation • 20 Feb 2024 • Xiao Li, Sichen Liu, Bolin Zhu, Yin Zhu, Yiwei Liu, Gong Cheng
The application of formulas is a fundamental ability of humans when addressing numerical reasoning problems.
no code implementations • 11 Dec 2023 • Xiao Li, Yutong Li, Anouck Girard, Ilya Kolmanovsky
The Neural Network (NN), as a black-box function approximator, has been considered in many control and robotics applications.
no code implementations • 2 Dec 2023 • Junwen Qiu, Xiao Li, Andre Milzarek
In this work, we design a new normal map-based proximal random reshuffling (norm-PRR) method for nonsmooth nonconvex finite-sum problems.
no code implementations • 26 Nov 2023 • Weijie Jin, Jing Zhang, Chao-Kai Wen, Shi Jin, Xiao Li, Shuangfeng Han
Reconfigurable intelligent surfaces (RIS) can improve signal propagation environments by adjusting the phase of the incident signal.
no code implementations • 20 Nov 2023 • Hengxu Yu, Xiao Li
This criterion is guaranteed to be triggered after a finite number of iterations, and then $\mathsf{RR}$-$\mathsf{sc}$ returns an iterate with its gradient below $\varepsilon$ with high probability.
1 code implementation • 13 Nov 2023 • Xiao Li, Huan Li, Hua Lu, Christian S. Jensen, Varun Pandey, Volker Markl
First, we propose a message propagation imputation network (MPIN) that is able to recover the missing values of data instances in a time window.
no code implementations • 6 Nov 2023 • Jiadi Zhang, Xiao Li, Mohammad Reza Amini, Ilya Kolmanovsky, Munechika Tsutsumi, Hayato Nakada
This paper presents the results of developing a multi-layer Neural Network (NN) to represent diesel engine emissions and integrating this NN into control design.
no code implementations • 6 Nov 2023 • Jiadi Zhang, Xiao Li, Ilya Kolmanovsky, Munechika Tsutsumi, Hayato Nakada
The developments described in the paper are based on a high-fidelity model of the engine airpath and torque response in GT-Power, which is extended with a feedforward neural network (FNN)-based model of engine out (feedgas) emissions identified from experimental engine data to enable the controller co-simulation and performance verification.
1 code implementation • 6 Nov 2023 • Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu
To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks.
no code implementations • 31 Oct 2023 • Xiao Li, Kaiwen Liu, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky
Autonomous vehicles need to accomplish their tasks while interacting with human drivers in traffic.
1 code implementation • 24 Oct 2023 • Pengyu Li, Yutong Wang, Xiao Li, Qing Qu
We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC).
no code implementations • 14 Oct 2023 • Xiao Li, Weili Wu
Moreover, the exploration of FL with multiple aggregators in edge computing is still new in the literature.
1 code implementation • NeurIPS 2023 • Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu
In the past few years, there has been an explosive surge in the use of machine learning (ML) techniques to address combinatorial optimization (CO) problems, especially mixed-integer linear programs (MILPs).
no code implementations • 25 Sep 2023 • Xiao Li, Kaiwen Liu, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky
Understanding the intention of vehicles in the surrounding traffic is crucial for an autonomous vehicle to successfully accomplish its driving tasks in complex traffic scenarios such as highway forced merging.
no code implementations • 23 Sep 2023 • Peiwen Jiang, Chao-Kai Wen, Xinping Yi, Xiao Li, Shi Jin, Jun Zhang
Foundation models (FMs), including large language models, have become increasingly popular due to their wide-ranging applicability and ability to understand human-like semantics.
no code implementations • 19 Sep 2023 • Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma
However, catastrophic forgetting, a notorious phenomenon where the fine-tuned model fails to retain similar performance compared to the pre-trained model, still remains an inherent problem in multimodal LLMs (MLLM).
no code implementations • 13 Sep 2023 • Ying Chen, Xiao Li, Hongbo Zhang, Wenyang Song, Chongxuan Xv
The adaptive graph convolution learns the relationship between different water quality parameters, updates the state information of each parameter, and improves the learning ability of the update relationship between nodes.
no code implementations • 10 Sep 2023 • Yaonai Wei, Tuo Zhang, Han Zhang, Tianyang Zhong, Lin Zhao, Zhengliang Liu, Chong Ma, Songyao Zhang, Muheng Shang, Lei Du, Xiao Li, Tianming Liu, Junwei Han
In this study, we propose a method called Chat2Brain that combines LLMs to basic text-2-image model, known as Text2Brain, to map open-ended semantic queries to brain activation maps in data-scarce and complex query environments.
no code implementations • 23 Aug 2023 • Xiao Li, Pan He, Aotian Wu, Sanjay Ranka, Anand Rangarajan
We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios.
no code implementations • ICCV 2023 • Yushuang Wu, Xiao Li, Jinglu Wang, Xiaoguang Han, Shuguang Cui, Yan Lu
Specifically, we use a small network similar to NeRF while preserving the rendering speed with a single network forwarding per pixel as in NeLF.
no code implementations • 7 Aug 2023 • Kaixuan Wei, Xiao Li, Johannes Froech, PRANEETH CHAKRAVARTHULA, James Whitehead, Ethan Tseng, Arka Majumdar, Felix Heide
The explosive growth of computation and energy cost of artificial intelligence has spurred strong interests in new computing modalities as potential alternatives to conventional electronic processors.
no code implementations • 5 Aug 2023 • PRANEETH CHAKRAVARTHULA, Jipeng Sun, Xiao Li, Chenyang Lei, Gene Chou, Mario Bijelic, Johannes Froesch, Arka Majumdar, Felix Heide
The optical array is embedded on a metasurface that, at 700~nm height, is flat and sits on the sensor cover glass at 2. 5~mm focal distance from the sensor.
no code implementations • 27 May 2023 • Xiao Li, Hang Chen, Xiaolin Hu
We argue that using adversarially pre-trained backbone networks is essential for enhancing the adversarial robustness of object detectors.
1 code implementation • NeurIPS 2023 • Huikang Liu, Xiao Li, Anthony Man-Cho So
This work presents ReSync, a Riemannian subgradient-based algorithm for solving the robust rotation synchronization problem, which arises in various engineering applications.
no code implementations • 23 May 2023 • Xiao Li, Lei Zhao, Daoli Zhu, Anthony Man-Cho So
In particular, when $f$ is convex, we show $\mathcal{O}(\log(k)/\sqrt{k})$ rate of convergence in terms of the suboptimality gap.
no code implementations • CVPR 2023 • Yue Gao, Yuan Zhou, Jinglu Wang, Xiao Li, Xiang Ming, Yan Lu
Our method leverages both self-supervised learned landmarks and 3D face model-based landmarks to model the motion.
1 code implementation • CVPR 2023 • Yushuang Wu, Zizheng Yan, Ce Chen, Lai Wei, Xiao Li, Guanbin Li, Yihao Li, Shuguang Cui, Xiaoguang Han
Thus, we propose a new task, SCoDA, for the domain adaptation of real scan shape completion from synthetic data.
1 code implementation • CVPR 2023 • Kun Yan, Xiao Li, Fangyun Wei, Jinglu Wang, Chenbin Zhang, Ping Wang, Yan Lu
The underlying idea is to generate pseudo labels for unlabeled frames during training and to optimize the model on the combination of labeled and pseudo-labeled data.
no code implementations • CVPR 2023 • Mingfang Zhang, Jinglu Wang, Xiao Li, Yifei HUANG, Yoichi Sato, Yan Lu
The Multiplane Image (MPI), containing a set of fronto-parallel RGBA layers, is an effective and efficient representation for view synthesis from sparse inputs.
1 code implementation • 7 Mar 2023 • Haocheng Ju, Haimiao Zhang, Lin Li, Xiao Li, Bin Dong
Joint channel estimation and signal detection (JCESD) in wireless communication systems is a crucial and challenging task, especially since it inherently poses a nonlinear inverse problem.
no code implementations • 30 Jan 2023 • Kun Huang, Xiao Li, Shi Pu
Distributed stochastic optimization has drawn great attention recently due to its effectiveness in solving large-scale machine learning problems.
1 code implementation • 30 Jan 2023 • Xiao Li, Wei zhang, Yining Liu, Zhanhao Hu, Bo Zhang, Xiaolin Hu
Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero-shot adversarial robustness an open question.
no code implementations • 25 Jan 2023 • Aotian Wu, Pan He, Xiao Li, Ke Chen, Sanjay Ranka, Anand Rangarajan
Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models.
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 • ICCV 2023 • Xiang Li, Jinglu Wang, Xiaohao Xu, Xiao Li, Bhiksha Raj, Yan Lu
Our model achieves state-of-the-art performance on R-VOS benchmarks, Ref-DAVIS17 and Ref-Youtube-VOS, and also our RRYTVOS dataset.
no code implementations • 23 Dec 2022 • Xiao Li, Sheng Liu, Jinxin Zhou, Xinyu Lu, Carlos Fernandez-Granda, Zhihui Zhu, Qing Qu
As model size continues to grow and access to labeled training data remains limited, transfer learning has become a popular approach in many scientific and engineering fields.
1 code implementation • 4 Dec 2022 • Xiao Li, Ziqi Wang, Bo Zhang, Fuchun Sun, Xiaolin Hu
The first stage of ROCK corresponds to the process of decomposing objects into parts in human vision.
1 code implementation • 23 Nov 2022 • Xiao Li, Yin Zhu, Sichen Liu, Jiangzhou Ju, Yuzhong Qu, Gong Cheng
Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community.
no code implementations • 9 Oct 2022 • Xiu Li, Xiao Li, Yan Lu
A high-quality NeRF decomposition relies on good geometry information extraction as well as good prior terms to properly resolve ambiguities between different components.
no code implementations • 4 Oct 2022 • Jinxin Zhou, Chong You, Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu
We extend such results and show through global solution and landscape analyses that a broad family of loss functions including commonly used label smoothing (LS) and focal loss (FL) exhibits Neural Collapse.
no code implementations • 18 Aug 2022 • Gusi Te, Xiu Li, Xiao Li, Jinglu Wang, Wei Hu, Yan Lu
We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views.
1 code implementation • 17 Aug 2022 • Xiao Li, Qiongxiu Li, Zhanhao Hu, Xiaolin Hu
We demonstrate that the generalization gap and privacy leakage are less correlated than those of the previous results.
1 code implementation • 4 Jul 2022 • Xiang Li, Jinglu Wang, Xiaohao Xu, Xiao Li, Bhiksha Raj, Yan Lu
Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression.
Ranked #11 on Referring Video Object Segmentation on Refer-YouTube-VOS
Referring Expression Segmentation Referring Video Object Segmentation +2
no code implementations • 30 Jun 2022 • Lei Zhao, Ding Chen, Daoli Zhu, Xiao Li
For the case when $f$ is weakly convex and its subdifferential satisfies the global metric subregularity property, we derive the $\mathcal{O}(\varepsilon^{-4})$ iteration complexity in expectation.
no code implementations • 30 Jun 2022 • Jiajia Guo, Chao-Kai Wen, Shi Jin, Xiao Li
This article provides a guideline for the standardization study of AI-based CSI feedback enhancement.
no code implementations • 12 Jun 2022 • Qijun Luo, Xiao Li
Most of the existing finite-time convergence results are derived based on either double-loop update or two-timescale step sizes rule, and this is the case even for centralized AC algorithm under a single-agent setting.
no code implementations • 8 Jun 2022 • Xiao Li, Andre Milzarek
In this work, we provide a fundamental unified convergence theorem used for deriving expected and almost sure convergence results for a series of stochastic optimization methods.
1 code implementation • ACL 2022 • Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun, Yuzhong Qu
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text.
no code implementations • 2 Mar 2022 • Jinxin Zhou, Xiao Li, Tianyu Ding, Chong You, Qing Qu, Zhihui Zhu
When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to the vertices of a Simplex Equiangular Tight Frame (ETF) up to scaling, and (ii) cross-example within-class variability of last-layer activations collapses to zero.
no code implementations • 31 Dec 2021 • Kun Huang, Xiao Li, Andre Milzarek, Shi Pu, Junwen Qiu
We show that D-RR inherits favorable characteristics of RR for both smooth strongly convex and smooth nonconvex objective functions.
1 code implementation • 6 Dec 2021 • Xiaohao Xu, Jinglu Wang, Xiao Li, Yan Lu
We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively.
Ranked #3 on Video Object Segmentation on DAVIS 2017 (test-dev)
no code implementations • 3 Dec 2021 • Xiang Li, Jinglu Wang, Xiao Li, Yan Lu
Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames.
no code implementations • 22 Nov 2021 • Wei Xiao, Ramin Hasani, Xiao Li, Daniela Rus
This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems.
no code implementations • 20 Oct 2021 • Xiang Li, Jinglu Wang, Xiao Li, Yan Lu
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.
no code implementations • 10 Oct 2021 • Xiao Li, Andre Milzarek, Junwen Qiu
We conduct a novel convergence analysis for the non-descent RR method with diminishing step sizes based on the KL inequality, which generalizes the standard KL framework.
1 code implementation • 5 Oct 2021 • Xiao Li, Yidong Du, Zhen Zeng, Odest Chadwicke Jenkins
This paper proposes a SEmantic understANding Network (SeanNet) architecture that enables an effective learning process with coupled visual and semantic inputs.
no code implementations • 29 Sep 2021 • Lei Zhao, Daoli Zhu, Xiao Li
The large-scale linearly constrained nonsmooth nonconvex optimization finds wide applications in machine learning, including non-PSD Kernel SVM, linearly constrained Lasso with nonsmooth nonconvex penalty, etc.
1 code implementation • 23 May 2021 • Lu He, Qianyu Zhou, Xiangtai Li, Li Niu, Guangliang Cheng, Xiao Li, Wenxuan Liu, Yunhai Tong, Lizhuang Ma, Liqing Zhang
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
no code implementations • 9 May 2021 • YiMin Dou, Kewen Li, Jianbing Zhu, Xiao Li, Yingjie Xi
The task of image segmentation requires huge labels, especially 3D seismic data, which has a complex structure and lots of noise.
1 code implementation • NeurIPS 2021 • Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu
In contrast to existing landscape analysis for deep neural networks which is often disconnected from practice, our analysis of the simplified model not only does it explain what kind of features are learned in the last layer, but it also shows why they can be efficiently optimized in the simplified settings, matching the empirical observations in practical deep network architectures.
no code implementations • 14 Apr 2021 • Xiao Li, Chongru Liu, Jin Ma
The line potential energy in the cutset is used as the criterion for monitoring the generator instability, but the criterion has the following two limitations due to narrowly defined conditions.
2 code implementations • CVPR 2021 • Chufeng Tang, Hang Chen, Xiao Li, Jianmin Li, Zhaoxiang Zhang, Xiaolin Hu
Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory.
no code implementations • 3 Mar 2021 • Xiao Huang, Di Zhu, Fan Zhang, Tao Liu, Xiao Li, Lei Zou
The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted.
1 code implementation • NeurIPS 2021 • Sheng Liu, Xiao Li, Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu
Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets.
no code implementations • 24 Feb 2021 • Brandon Araki, Xiao Li, Kiran Vodrahalli, Jonathan DeCastro, Micah J. Fry, Daniela Rus
Learning composable policies for environments with complex rules and tasks is a challenging problem.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 23 Feb 2021 • Merle Behr, Yu Wang, Xiao Li, Bin Yu
Iterative Random Forests (iRF) use a tree ensemble from iteratively modified RF to obtain predictive and stable non-linear or Boolean interactions of features.
Statistics Theory Statistics Theory
1 code implementation • 23 Feb 2021 • Xiao Li, Jianmin Li, Ting Dai, Jie Shi, Jun Zhu, Xiaolin Hu
A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53. 95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A.
no code implementations • 16 Feb 2021 • Ke Huang, Yu Wang, Xiao Li
Recently a class of quantum systems exhibiting weak ergodicity breaking has attracted much attention.
Disordered Systems and Neural Networks Statistical Mechanics
no code implementations • 1 Feb 2021 • Qisheng Wang, Xiao Li, Shi Jin, Yijiain Chen
In this letter, we investigate the hybrid beamforming based on deep reinforcement learning (DRL) for millimeter Wave (mmWave) multi-user (MU) multiple-input-single-output (MISO) system.
no code implementations • 20 Jan 2021 • Xiaopei Zhu, Xiao Li, Jianmin Li, Zheyao Wang, Xiaolin Hu
By using a combination method, we successfully hide from the visible light and infrared object detection systems at the same time.
1 code implementation • 14 Jan 2021 • Xiao Li, Yawei Sun, Gong Cheng
To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator.
no code implementations • COLING 2020 • Xiao Li, Yu Hong, Huibin Ruan, Zhen Huang
We tackle implicit discourse relation classification, a task of automatically determining semantic relationships between arguments.
1 code implementation • 11 Nov 2020 • Xiao Li, Michele Guindani, Chaan S. Ng, Brian P. Hobbs
Cancer radiomics is an emerging discipline promising to elucidate lesion phenotypes and tumor heterogeneity through patterns of enhancement, texture, morphology, and shape.
Applications
1 code implementation • COLING 2020 • Ruizhe Li, Xiao Li, Guanyi Chen, Chenghua Lin
The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences.
no code implementations • EMNLP 2020 • Xiao Li, Guanyi Chen, Chenghua Lin, Ruizhe Li
We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer.
no code implementations • 28 Sep 2020 • Jie Yang, Jing Xu, Xiao Li, Shi Jin, Bo Gao
As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.
no code implementations • 21 Aug 2020 • Xiao Li, Weili Wu
Bitcoin, as one of the most popular cryptocurrency, is recently attracting much attention of investors.
no code implementations • ACL 2020 • Yirong Pan, Xiao Li, Yating Yang, Rui Dong
Neural machine translation (NMT) has achieved impressive performance recently by using large-scale parallel corpora.
no code implementations • 2 Jun 2020 • Minxuan Lin, Fan Tang, Wei-Ming Dong, Xiao Li, Chongyang Ma, Changsheng Xu
Currently, there are few methods that can perform both multimodal and multi-domain stylization simultaneously.
no code implementations • 16 May 2020 • Xiao Li, Kees Van Deemter, Chenghua Lin
Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques.
1 code implementation • 16 May 2020 • Nick Altieri, Rebecca L. Barter, James Duncan, Raaz Dwivedi, Karl Kumbier, Xiao Li, Robert Netzorg, Briton Park, Chandan Singh, Yan Shuo Tan, Tiffany Tang, Yu Wang, Chao Zhang, Bin Yu
We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.
no code implementations • ICLR 2020 • Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu
Learning overcomplete representations finds many applications in machine learning and data analytics.
no code implementations • 30 Apr 2020 • Jing Han, Kun Qian, Meishu Song, Zijiang Yang, Zhao Ren, Shuo Liu, Juan Liu, Huaiyuan Zheng, Wei Ji, Tomoya Koike, Xiao Li, Zixing Zhang, Yoshiharu Yamamoto, Björn W. Schuller
In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety.
no code implementations • 17 Apr 2020 • Xiao Li, Hanchen Xu, Jinming Zhang, Hua-hua Chang
In this paper, we formulate the adaptive learning problem---the problem of how to find an individualized learning plan (called policy) that chooses the most appropriate learning materials based on learner's latent traits---faced in adaptive learning systems as a Markov decision process (MDP).
no code implementations • 24 Mar 2020 • Björn W. Schuller, Dagmar M. Schuller, Kun Qian, Juan Liu, Huaiyuan Zheng, Xiao Li
We come to the conclusion that CA appears ready for implementation of (pre-)diagnosis and monitoring tools, and more generally provides rich and significant, yet so far untapped potential in the fight against COVID-19 spread.
no code implementations • 20 Jan 2020 • Qing Qu, Zhihui Zhu, Xiao Li, Manolis C. Tsakiris, John Wright, René Vidal
The problem of finding the sparsest vector (direction) in a low dimensional subspace can be considered as a homogeneous variant of the sparse recovery problem, which finds applications in robust subspace recovery, dictionary learning, sparse blind deconvolution, and many other problems in signal processing and machine learning.
no code implementations • 2 Jan 2020 • Yirong Pan, Xiao Li, Yating Yang, Rui Dong
Experimental results show that our morphologically motivated word segmentation method is better suitable for the NMT model, which achieves significant improvements on Turkish-English and Uyghur-Chinese machine translation tasks on account of reducing data sparseness and language complexity.
no code implementations • 20 Dec 2019 • Wankai Tang, Jun Yan Dai, Ming Zheng Chen, Kai-Kit Wong, Xiao Li, Xinsheng Zhao, Shi Jin, Qiang Cheng, Tie Jun Cui
Reconfigurable intelligent surface (RIS) is a new paradigm that has great potential to achieve cost-effective, energy-efficient information modulation for wireless transmission, by the ability to change the reflection coefficients of the unit cells of a programmable metasurface.
no code implementations • 5 Dec 2019 • Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu
In this work, we show these problems can be formulated as $\ell^4$-norm optimization problems with spherical constraint, and study the geometric properties of their nonconvex optimization landscapes.
1 code implementation • WS 2019 • Ruizhe Li, Xiao Li, Chenghua Lin, Matthew Collinson, Rui Mao
Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data.
1 code implementation • 12 Nov 2019 • Xiao Li, Shixiang Chen, Zengde Deng, Qing Qu, Zhihui Zhu, Anthony Man Cho So
To the best of our knowledge, these are the first convergence guarantees for using Riemannian subgradient-type methods to optimize a class of nonconvex nonsmooth functions over the Stiefel manifold.
no code implementations • 7 Nov 2019 • Keming Feng, Xiao Li, Yu Han, Shi Jin, Yijian Chen
In this letter, the use of intelligent reflecting surface (IRS) to enhance the physical layer security of downlink wireless communication is investigated.
1 code implementation • NeurIPS 2019 • Qing Qu, Xiao Li, Zhihui Zhu
We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel $\mathbf a$ and multiple sparse inputs $\{\mathbf x_i\}_{i=1}^p$ from their circulant convolution $\mathbf y_i = \mathbf a \circledast \mathbf x_i $ ($i=1,\cdots, p$).
no code implementations • IJCNLP 2019 • Zixian Huang, Yulin Shen, Xiao Li, Yuang Wei, Gong Cheng, Lin Zhou, Xin-yu Dai, Yuzhong Qu
Scenario-based question answering (SQA) has attracted increasing research attention.
no code implementations • 31 Jul 2019 • Qisheng Wang, Keming Feng, Xiao Li, Shi Jin
In this letter, we investigate the hybrid beamforming for millimeter wave massive multiple-input multiple-output (MIMO) system based on deep reinforcement learning (DRL).
2 code implementations • ICML 2020 • Xiao Li, Chenghua Lin, Ruizhe Li, Chaozheng Wang, Frank Guerin
We demonstrate the utility of our method for attribute manipulation in autoencoders trained across varied domains, using both human evaluation and automated methods.
Ranked #7 on Image Generation on CelebA 256x256 (FID metric)
3 code implementations • NeurIPS 2019 • Xiao Li, Yu Wang, Sumanta Basu, Karl Kumbier, Bin Yu
Based on the original definition of MDI by Breiman et al. for a single tree, we derive a tight non-asymptotic bound on the expected bias of MDI importance of noisy features, showing that deep trees have higher (expected) feature selection bias than shallow ones.
no code implementations • CVPR 2019 • Xiao Li, Yue Dong, Pieter Peers, Xin Tong
Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes.
no code implementations • ICLR 2019 • Xiao Li, Yao Ma, Calin Belta
Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task.
no code implementations • 28 Apr 2019 • Hanchen Xu, Xiao Li, Xiangyu Zhang, Junbo Zhang
In this letter, we address the problem of controlling energy storage systems (ESSs) for arbitrage in real-time electricity markets under price uncertainty.
no code implementations • 27 Mar 2019 • Jun Gao, Xiao Li, Li-Wei Wang, Sanja Fidler, Stephen Lin
We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline.
no code implementations • 23 Mar 2019 • Xiao Li, Calin Belta
We combine temporal logic with control Lyapunov functions to improve exploration.
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.
no code implementations • WS 2018 • Xiao Li, Kees Van Deemter, Chenghua Lin
This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully.
no code implementations • CONLL 2019 • Ruizhe Li, Chenghua Lin, Matthew Collinson, Xiao Li, Guanyi Chen
Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition.
Ranked #4 on Dialogue Act Classification on Switchboard corpus
no code implementations • 12 Oct 2018 • Xiao Li, Hanchen Xu, Jinming Zhang, Hua-hua Chang
To this end, we first develop a model for students' hierarchical skills in the E-learning system.
no code implementations • 24 Sep 2018 • Xiao Li, Zhihui Zhu, Anthony Man-Cho So, Rene Vidal
In this paper we study the problem of recovering a low-rank matrix from a number of random linear measurements that are corrupted by outliers taking arbitrary values.
Information Theory Information Theory
no code implementations • 17 Sep 2018 • Xiao Li, Yao Ma, Calin Belta
Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals.
no code implementations • ICLR 2018 • Xiao Li, Yao Ma, Calin Belta
An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large number of interactions with the environment in order to master a skill.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 31 Oct 2017 • Xiao Li, Yao Ma, Calin Belta
Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 27 Sep 2017 • Xiao Li, Yao Ma, Calin Belta
In this paper, we explore the use of temporal logic (TL) to specify tasks in reinforcement learning.
no code implementations • 19 Sep 2017 • Tao Hong, Xiao Li, Zhihui Zhu, Qiuwei Li
We consider designing a robust structured sparse sensing matrix consisting of a sparse matrix with a few non-zero entries per row and a dense base matrix for capturing signals efficiently We design the robust structured sparse sensing matrix through minimizing the distance between the Gram matrix of the equivalent dictionary and the target Gram of matrix holding small mutual coherence.
no code implementations • RANLP 2017 • Chenggang Mi, Yating Yang, Rui Dong, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang
To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach.
no code implementations • WS 2017 • Kees van Deemter, Le Sun, Rint Sybesma, Xiao Li, Bo Chen, Muyun Yang
East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number.
no code implementations • 11 Dec 2016 • Xiao Li, Cristian-Ioan Vasile, Calin Belta
We propose Truncated Linear Temporal Logic (TLTL) as specifications language, that is arguably well suited for the robotics applications, together with quantitative semantics, i. e., robustness degree.
no code implementations • 20 Jun 2016 • Xiao Li, Calin Belta
Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon and the inverted helicopter flight.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • NeurIPS 2015 • Xiao Li, Kannan Ramchandran
By writing the cut function as a polynomial and exploiting the graph structure, we propose a sketching algorithm to learn the an arbitrary $n$-node unknown graph using only few cut queries, which scales {\it almost linearly} in the number of edges and {\it sub-linearly} in the graph size $n$.
3 code implementations • 26 Aug 2015 • Xiao Li, Joseph K. Bradley, Sameer Pawar, Kannan Ramchandran
We consider the problem of computing the Walsh-Hadamard Transform (WHT) of some $N$-length input vector in the presence of noise, where the $N$-point Walsh spectrum is $K$-sparse with $K = {O}(N^{\delta})$ scaling sub-linearly in the input dimension $N$ for some $0<\delta<1$.