Search Results for author: Liang Xu

Found 55 papers, 23 papers with code

Cipher – Faoi Gheasa: A Game-with-a-Purpose for Irish

no code implementations CLTW (LREC) 2022 Elaine Uí Dhonnchadha, Monica Ward, Liang Xu

This paper describes Cipher – Faoi Gheasa, a ‘game with a purpose’ designed to support the learning of Irish in a fun and enjoyable way.

How NLP Can Strengthen Digital Game Based Language Learning Resources for Less Resourced Languages

no code implementations games (LREC) 2022 Monica Ward, Liang Xu, Elaine Uí Dhonnchadha

This paper provides an overview of the Cipher engine which enables the development of a Digital Educational Game (DEG) based on noticing ciphers or patterns in texts.

A Corpus-based Study of Corporate Image Represented in Corporate Social Responsibility Report: A Case Study of China Mobile and Vodafone

no code implementations CSRNLP (LREC) 2022 Xing Chen, Liang Xu

By examination of the high-frequency nouns, verbs, and keywords, the present study probes into the similarities and differences of corporate images represented in Corporate Social Responsibility (CSR) reports of China Mobile and Vodafone.

Cultural Vocal Bursts Intensity Prediction

Faoi Gheasa an adaptive game for Irish language learning

no code implementations ComputEL (ACL) 2022 Liang Xu, Elaine Uí Dhonnchadha, Monica Ward

This paper will focus on the language materials development as this is a bottleneck in the teaching and learning of minority and endangered languages.

SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications

no code implementations29 Apr 2024 Liang Xu, Lei Zhu, Yaotong Wu, Hang Xue

The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs).

Computational Efficiency Logical Reasoning +1

Neural Exponential Stabilization of Control-affine Nonlinear Systems

1 code implementation26 Mar 2024 Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate

Third, this parametrization and the inequality condition enable the design of contractivity-enforcing regularizers, which can be incorporated while designing the NN controller for exponential stabilization of the underlying nonlinear systems.

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning

1 code implementation14 Mar 2024 Xiuqin Zhong, Shengyuan Yan, Gongqi Lin, Hongguang Fu, Liang Xu, Siwen Jiang, Lei Huang, Wei Fang

However, adding auxiliary components automatically is challenging due to the complexity in selecting suitable auxiliary components especially when pivotal decisions have to be made.

Graph Attention Language Modelling +3

Structured Deep Neural Networks-Based Backstepping Trajectory Tracking Control for Lagrangian Systems

no code implementations1 Mar 2024 Jiajun Qian, Liang Xu, Xiaoqiang Ren, Xiaofan Wang

In addition, improved control performance can be achieved by further optimizing neural network parameters.

SuperCLUE-Math6: Graded Multi-Step Math Reasoning Benchmark for LLMs in Chinese

1 code implementation22 Jan 2024 Liang Xu, Hang Xue, Lei Zhu, Kangkang Zhao

We introduce SuperCLUE-Math6(SC-Math6), a new benchmark dataset to evaluate the mathematical reasoning abilities of Chinese language models.

Diversity GSM8K +2

Inter-X: Towards Versatile Human-Human Interaction Analysis

no code implementations CVPR 2024 Liang Xu, Xintao Lv, Yichao Yan, Xin Jin, Shuwen Wu, Congsheng Xu, Yifan Liu, Yizhou Zhou, Fengyun Rao, Xingdong Sheng, Yunhui Liu, Wenjun Zeng, Xiaokang Yang

We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects.

SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese

no code implementations9 Oct 2023 Liang Xu, Kangkang Zhao, Lei Zhu, Hang Xue

To systematically assess the safety of Chinese LLMs, we introduce SuperCLUE-Safety (SC-Safety) - a multi-round adversarial benchmark with 4912 open-ended questions covering more than 20 safety sub-dimensions.

Model Selection Natural Language Understanding

Duration-adaptive Video Highlight Pre-caching for Vehicular Communication Network

no code implementations5 Sep 2023 Liang Xu, Deshi Li, Kaitao Meng, Mingliu Liu, Shuya Zhu

Specifically, a highlight entropy model is devised with the consideration of the segments' popularity and continuity between segments within a period of time, based on which, an optimization problem of video highlight pre-caching is formulated.

Federated Learning in Big Model Era: Domain-Specific Multimodal Large Models

no code implementations22 Aug 2023 Zengxiang Li, Zhaoxiang Hou, Hui Liu, Ying Wang, Tongzhi Li, Longfei Xie, Chao Shi, Chengyi Yang, Weishan Zhang, Zelei Liu, Liang Xu

Preliminary experiments show that enterprises can enhance and accumulate intelligent capabilities through multimodal model federated learning, thereby jointly creating an smart city model that provides high-quality intelligent services covering energy infrastructure safety, residential community security, and urban operation management.

Federated Learning Management

MCPA: Multi-scale Cross Perceptron Attention Network for 2D Medical Image Segmentation

1 code implementation27 Jul 2023 Liang Xu, Mingxiao Chen, Yi Cheng, Pengfei Shao, Shuwei Shen, Peng Yao, Ronald X. Xu

The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales.

Image Segmentation Medical Image Segmentation +2

SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark

no code implementations27 Jul 2023 Liang Xu, Anqi Li, Lei Zhu, Hang Xue, Changtai Zhu, Kangkang Zhao, Haonan He, Xuanwei Zhang, Qiyue Kang, Zhenzhong Lan

We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE.

Language Modelling Large Language Model

A Surrogate Data Assimilation Model for the Estimation of Dynamical System in a Limited Area

no code implementations14 Jul 2023 Wei Kang, Liang Xu, Hong Zhou

We propose a novel learning-based surrogate data assimilation (DA) model for efficient state estimation in a limited area.

P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification

no code implementations24 May 2023 Xiyuan Wang, Fangyuan Wang, Bo Xu, Liang Xu, Jing Xiao

Typically, the Time-Delay Neural Network (TDNN) and Transformer can serve as a backbone for Speaker Verification (SV).

Speaker Verification

Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification

no code implementations24 May 2022 Liang Xu, Yi Cheng, Fan Zhang, Bingxuan Wu, Pengfei Shao, Peng Liu, Shuwei Shen, Peng Yao, Ronald X. Xu

This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties.

Classification imbalanced classification +1

Robust Classification using Contractive Hamiltonian Neural ODEs

1 code implementation22 Mar 2022 Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate

Since in NODEs the input data corresponds to the initial condition of dynamical systems, we show contractivity can mitigate the effect of input perturbations.

Classification Image Classification +1

ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation

no code implementations ICCV 2023 Liang Xu, Ziyang Song, Dongliang Wang, Jing Su, Zhicheng Fang, Chenjing Ding, Weihao Gan, Yichao Yan, Xin Jin, Xiaokang Yang, Wenjun Zeng, Wei Wu

We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions.

HAKE: A Knowledge Engine Foundation for Human Activity Understanding

3 code implementations14 Feb 2022 Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, Zuoyu Qiu, Liang Xu, Yue Xu, Hao-Shu Fang, Cewu Lu

Human activity understanding is of widespread interest in artificial intelligence and spans diverse applications like health care and behavior analysis.

Action Recognition Human-Object Interaction Detection +2

The Observability in Unobservable Systems

no code implementations11 Jan 2022 Wei Kang, Liang Xu, Hong Zhou

In this paper, we introduce the concept of observability of targeted state variables for systems that may not be fully observable.

Data-Driven Computational Methods for the Domain of Attraction and Zubov's Equation

no code implementations29 Dec 2021 Wei Kang, Kai Sun, Liang Xu

We prove that a neural network approximation exists for the Lyapunov function of power systems such that the approximation error is a cubic polynomial of the number of generators.

Neural Energy Casimir Control for Port-Hamiltonian Systems

1 code implementation6 Dec 2021 Liang Xu, Muhammad Zakwan, Giancarlo Ferrari-Trecate

The energy Casimir method is an effective controller design approach to stabilize port-Hamiltonian systems at a desired equilibrium.

DataCLUE: A Benchmark Suite for Data-centric NLP

1 code implementation16 Nov 2021 Liang Xu, Jiacheng Liu, Xiang Pan, Xiaojing Lu, Xiaofeng Hou

However, we have not seen significant research progress in this field, especially in NLP.

Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning

1 code implementation10 Oct 2021 Shaohua Wu, Xudong Zhao, Tong Yu, Rongguo Zhang, Chong Shen, Hongli Liu, Feng Li, Hong Zhu, Jiangang Luo, Liang Xu, Xuanwei Zhang

With this method, Yuan 1. 0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks.

Few-Shot Learning Language Modelling +1

Non Vanishing Gradients for Arbitrarily Deep Neural Networks: a Hamiltonian System Approach

no code implementations NeurIPS Workshop DLDE 2021 Clara Galimberti, Luca Furieri, Liang Xu, Giancarlo Ferrari-Trecate

Deep Neural Networks (DNNs) training can be difficult due to vanishing or exploding gradients during weight optimization through backpropagation.

FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark

1 code implementation15 Jul 2021 Liang Xu, Xiaojing Lu, Chenyang Yuan, Xuanwei Zhang, Huilin Xu, Hu Yuan, Guoao Wei, Xiang Pan, Xin Tian, Libo Qin, Hu Hai

While different learning schemes -- fine-tuning, zero-shot, and few-shot learning -- have been widely explored and compared for languages such as English, there is comparatively little work in Chinese to fairly and comprehensively evaluate and compare these methods and thus hinders cumulative progress.

Few-Shot Learning Machine Reading Comprehension +4

Evaluating Modules in Graph Contrastive Learning

1 code implementation15 Jun 2021 Ganqu Cui, Yufeng Du, Cheng Yang, Jie zhou, Liang Xu, Xing Zhou, Xingyi Cheng, Zhiyuan Liu

The recent emergence of contrastive learning approaches facilitates the application on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature.

Contrastive Learning Graph Classification +1

Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design

3 code implementations27 May 2021 Clara Lucía Galimberti, Luca Furieri, Liang Xu, Giancarlo Ferrari-Trecate

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation.

Image Classification

A unified framework for Hamiltonian deep neural networks

2 code implementations27 Apr 2021 Clara L. Galimberti, Liang Xu, Giancarlo Ferrari Trecate

Training deep neural networks (DNNs) can be difficult due to the occurrence of vanishing/exploding gradients during weight optimization.

An Alignment-Agnostic Model for Chinese Text Error Correction

no code implementations Findings (EMNLP) 2021 Liying Zheng, Yue Deng, Weishun Song, Liang Xu, Jing Xiao

Most existing models based on detect-correct framework can correct mistaken characters errors, but they cannot deal with missing or redundant characters.

Direct evidence of the gradient drift instability being the origin of a rotating spoke in a crossed field plasma

no code implementations11 Mar 2021 Liang Xu, Denis Eremin, Ralf Peter Brinkmann

A plasma rotating spoke in a crossed field discharge is studied using 2D radial-azimuthal fully kinetic Particle-In-Cell Monte Carlo Collision (PIC/MCC) simulations.

Super-Resolution Plasma Physics

Finite-sample-based Spectral Radius Estimation and Stabilizability Test for Networked Control Systems

no code implementations3 Mar 2021 Liang Xu, Giancarlo Ferrari-Trecate

In the analysis and control of discrete-time linear time-invariant systems, the spectral radius of the system state matrix plays an essential role.

Optimization and Control Systems and Control Systems and Control

Pushing the Envelope of Thin Crack Detection

no code implementations9 Jan 2021 Liang Xu, Taro Hatsutani, Xing Liu, Engkarat Techapanurak, Han Zou, Takayuki Okatani

We experimentally show that this makes it possible to detect cracks from an image of one-third the resolution of images used for annotation with about the same accuracy.

NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection

no code implementations8 Jan 2021 Liang Xu, Liying Zheng, Weijun Li, Zhenbo Chen, Weishun Song, Yue Deng, Yongzhe Chang, Jing Xiao, Bo Yuan

In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs).

Anomaly Detection Time Series +1

Quantum-limited Localisation and Resolution in Three Dimensions

no code implementations9 Dec 2020 Ben Wang, Liang Xu, Lijian Zhang

As a method to extract information from optical system, imaging can be viewed as a parameter estimation problem.

Quantum Physics Optics

On Consensusability of Linear Interconnected Multi-Agent Systems and Simultaneous Stabilization

no code implementations20 Oct 2020 Mustafa Sahin Turan, Liang Xu, Giancarlo Ferrari-Trecate

Consensusability of multi-agent systems (MASs) certifies the existence of a distributed controller capable of driving the states of each subsystem to a consensus value.

OCNLI: Original Chinese Natural Language Inference

1 code implementation Findings of the Association for Computational Linguistics 2020 Hai Hu, Kyle Richardson, Liang Xu, Lu Li, Sandra Kuebler, Lawrence S. Moss

In this paper, we present the first large-scale NLI dataset (consisting of ~56, 000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI).

Natural Language Inference Sentence +1

Cipher: A Prototype Game-with-a-Purpose for Detecting Errors in Text

no code implementations LREC 2020 Liang Xu, Jon Chamberlain

Errors commonly exist in machine-generated documents and publication materials; however, some correction algorithms do not perform well for complex errors and it is costly to employ humans to do the task.

CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model

2 code implementations3 Mar 2020 Liang Xu, Xuanwei Zhang, Qianqian Dong

In this paper, we introduce the Chinese corpus from CLUE organization, CLUECorpus2020, a large-scale corpus that can be used directly for self-supervised learning such as pre-training of a language model, or language generation.

8k Language Modelling +2

CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese

3 code implementations13 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

3D Objectness Estimation via Bottom-up Regret Grouping

no code implementations5 Dec 2019 Zelin Ye, Yan Hao, Liang Xu, Rui Zhu, Cewu Lu

Further ablation study also demonstrates the effectiveness of our grouping predictor and regret mechanism.

HAKE: Human Activity Knowledge Engine

4 code implementations13 Apr 2019 Yong-Lu Li, Liang Xu, Xinpeng Liu, Xijie Huang, Yue Xu, Mingyang Chen, Ze Ma, Shiyi Wang, Hao-Shu Fang, Cewu Lu

To address these and promote the activity understanding, we build a large-scale Human Activity Knowledge Engine (HAKE) based on the human body part states.

Ranked #2 on Human-Object Interaction Detection on HICO (using extra training data)

Action Detection Human-Object Interaction Detection +1

Action Machine: Rethinking Action Recognition in Trimmed Videos

no code implementations14 Dec 2018 Jiagang Zhu, Wei Zou, Liang Xu, Yiming Hu, Zheng Zhu, Manyu Chang, Jun-Jie Huang, Guan Huang, Dalong Du

On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97. 2% and 94. 3% on cross-view and cross-subject respectively.

Action Recognition Multimodal Activity Recognition +3

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

3 code implementations CVPR 2019 Yong-Lu Li, Siyuan Zhou, Xijie Huang, Liang Xu, Ze Ma, Hao-Shu Fang, Yan-Feng Wang, Cewu Lu

On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results.

Human-Object Interaction Detection Object

Cannot find the paper you are looking for? You can Submit a new open access paper.