Search Results for author: Kun Xu

Found 79 papers, 47 papers with code

RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging

no code implementations EMNLP 2021 Jie Hao, Linfeng Song, LiWei Wang, Kun Xu, Zhaopeng Tu, Dong Yu

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.

Dialogue Rewriting Text Generation

Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution

no code implementations ACL 2022 Irene Li, Linfeng Song, Kun Xu, Dong Yu

Coreference resolution over semantic graphs like AMRs aims to group the graph nodes that represent the same entity.


Instance-adaptive training with noise-robust losses against noisy labels

no code implementations EMNLP 2021 Lifeng Jin, Linfeng Song, Kun Xu, Dong Yu

In order to alleviate the huge demand for annotated datasets for different tasks, many recent natural language processing datasets have adopted automated pipelines for fast-tracking usable data.

Understanding and Stabilizing GANs' Training Dynamics Using Control Theory

no code implementations ICML 2020 Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang

There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.

Harder Tasks Need More Experts: Dynamic Routing in MoE Models

1 code implementation12 Mar 2024 Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng

In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty.

Computational Efficiency

Probing Multimodal Large Language Models for Global and Local Semantic Representations

1 code implementation27 Feb 2024 Mingxu Tao, Quzhe Huang, Kun Xu, Liwei Chen, Yansong Feng, Dongyan Zhao

The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images.

object-detection Object Detection +1

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

1 code implementation5 Feb 2024 Yang Jin, Zhicheng Sun, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang song, Kun Gai, Yadong Mu

In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.

Video Understanding Visual Question Answering

A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models

1 code implementation13 Nov 2023 Hejing Cao, Zhenwei An, Jiazhan Feng, Kun Xu, Liwei Chen, Dongyan Zhao

While large language models exhibit remarkable performance in the Question Answering task, they are susceptible to hallucinations.

Question Answering

Exploring the Usage of Chinese Pinyin in Pretraining

no code implementations8 Oct 2023 Baojun Wang, Kun Xu, Lifeng Shang

Through delicate pretraining tasks, the characters and pinyin representation are fused, which can enhance the error tolerance for SSP errors.

Language Modelling

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

1 code implementation9 Sep 2023 Yang Jin, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Di Zhang, Wenwu Ou, Kun Gai, Yadong Mu

Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.

Language Modelling Large Language Model +1

Semantic optical fiber communication system

no code implementations27 Dec 2022 Zhenming Yu, Hongyu Huang, Liming Cheng, Wei zhang, Yueqiu Mu, Kun Xu

The current optical communication systems minimize bit or symbol errors without considering the semantic meaning behind digital bits, thus transmitting a lot of unnecessary information.

PaletteNeRF: Palette-based Color Editing for NeRFs

no code implementations25 Dec 2022 Qiling Wu, Jianchao Tan, Kun Xu

Instead of predicting pixel colors as in vanilla NeRFs, our method predicts additive weights.

Learning a Grammar Inducer from Massive Uncurated Instructional Videos

1 code implementation22 Oct 2022 Songyang Zhang, Linfeng Song, Lifeng Jin, Haitao Mi, Kun Xu, Dong Yu, Jiebo Luo

While previous work focuses on building systems for inducing grammars on text that are well-aligned with video content, we investigate the scenario, in which text and video are only in loose correspondence.

Language Acquisition Video Alignment

Neural Color Operators for Sequential Image Retouching

2 code implementations17 Jul 2022 Yili Wang, Xin Li, Kun Xu, Dongliang He, Qi Zhang, Fu Li, Errui Ding

The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar.

Image Enhancement Image Retouching

Discourse-Aware Graph Networks for Textual Logical Reasoning

no code implementations4 Jul 2022 Yinya Huang, Lemao Liu, Kun Xu, Meng Fang, Liang Lin, Xiaodan Liang

In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs).

graph construction Logical Reasoning +3

FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation

no code implementations2 May 2022 Yuansheng Wang, Wangbin Sun, Kun Xu, Zulun Zhu, Liang Chen, Zibin Zheng

Graph contrastive learning (GCL), as a popular approach to graph self-supervised learning, has recently achieved a non-negligible effect.

Contrastive Learning Data Augmentation +3

Distant finetuning with discourse relations for stance classification

no code implementations27 Apr 2022 Lifeng Jin, Kun Xu, Linfeng Song, Dong Yu

Approaches for the stance classification task, an important task for understanding argumentation in debates and detecting fake news, have been relying on models which deal with individual debate topics.

Classification Stance Classification

Zero-shot Cross-lingual Conversational Semantic Role Labeling

1 code implementation Findings (NAACL) 2022 Han Wu, Haochen Tan, Kun Xu, Shuqi Liu, Lianwei Wu, Linqi Song

While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training.

Response Generation Semantic Role Labeling

Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging

1 code implementation ICCV 2021 Ziyi Meng, Zhenming Yu, Kun Xu, Xin Yuan

In this paper, inspired by the untrained neural networks such as deep image priors (DIP) and deep decoders, we develop a framework by integrating DIP into the plug-and-play regime, leading to a self-supervised network for spectral SCI reconstruction.


Principle-driven Fiber Transmission Model based on PINN Neural Network

no code implementations24 Aug 2021 Yubin Zang, Zhenming Yu, Kun Xu, Xingzeng Lan, Minghua Chen, Sigang Yang, Hongwei Chen

Instead of adopting input signals and output signals which are calculated by SSFM algorithm in advance before training, this principle-driven PINN based fiber model adopts frames of time and distance as its inputs and the corresponding real and imaginary parts of NLSE solutions as its outputs.

Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment

1 code implementation CVPR 2021 Dongyu She, Yu-Kun Lai, Gaoxiong Yi, Kun Xu

The first LA-GCN module constructs an aesthetics-related graph in the coordinate space and performs reasoning over spatial nodes.

Domain-Adaptive Pretraining Methods for Dialogue Understanding

no code implementations ACL 2021 Han Wu, Kun Xu, Linfeng Song, Lifeng Jin, Haisong Zhang, Linqi Song

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks.

Dialogue Understanding

Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization

no code implementations NeurIPS 2021 Guoqiang Wu, Chongxuan Li, Kun Xu, Jun Zhu

Our results show that learning algorithms with the consistent univariate loss have an error bound of $O(c)$ ($c$ is the number of labels), while algorithms with the inconsistent pairwise loss depend on $O(\sqrt{c})$ as shown in prior work.

Computational Efficiency Multi-Label Classification

Conversational Semantic Role Labeling

no code implementations11 Apr 2021 Kun Xu, Han Wu, Linfeng Song, Haisong Zhang, Linqi Song, Dong Yu

Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence.

coreference-resolution Dialogue Understanding +3

Video-aided Unsupervised Grammar Induction

1 code implementation NAACL 2021 Songyang Zhang, Linfeng Song, Lifeng Jin, Kun Xu, Dong Yu, Jiebo Luo

We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video.

Optical Character Recognition (OCR)

GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software

1 code implementation16 Feb 2021 Jintang Li, Kun Xu, Liang Chen, Zibin Zheng, Xiao Liu

Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data.


Joint Coreference Resolution and Character Linking for Multiparty Conversation

1 code implementation EACL 2021 Jiaxin Bai, Hongming Zhang, Yangqiu Song, Kun Xu

Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations.

coreference-resolution Entity Linking

Robust Dialogue Utterance Rewriting as Sequence Tagging

1 code implementation29 Dec 2020 Jie Hao, Linfeng Song, LiWei Wang, Kun Xu, Zhaopeng Tu, Dong Yu

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.

Dialogue Rewriting Text Generation

Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models

1 code implementation NeurIPS Workshop ICBINB 2020 Fan Bao, Kun Xu, Chongxuan Li, Lanqing Hong, Jun Zhu, Bo Zhang

The learning and evaluation of energy-based latent variable models (EBLVMs) without any structural assumptions are highly challenging, because the true posteriors and the partition functions in such models are generally intractable.

Bi-level Score Matching for Learning Energy-based Latent Variable Models

1 code implementation NeurIPS 2020 Fan Bao, Chongxuan Li, Kun Xu, Hang Su, Jun Zhu, Bo Zhang

This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bi-level optimization problem.

Rolling Shutter Correction Stochastic Optimization

Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

no code implementations EMNLP 2020 Kun Xu, Haochen Tan, Linfeng Song, Han Wu, Haisong Zhang, Linqi Song, Dong Yu

For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance.

Dialogue Rewriting Semantic Role Labeling

Efficient Learning of Generative Models via Finite-Difference Score Matching

1 code implementation NeurIPS 2020 Tianyu Pang, Kun Xu, Chongxuan Li, Yang song, Stefano Ermon, Jun Zhu

Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation

1 code implementation CVPR 2021 Liwei Wang, Jing Huang, Yin Li, Kun Xu, Zhengyuan Yang, Dong Yu

Our core innovation is the learning of a region-phrase score function, based on which an image-sentence score function is further constructed.

Contrastive Learning Knowledge Distillation +6

ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT

no code implementations ACL 2020 Linfeng Song, Kun Xu, Yue Zhang, Jianshu Chen, Dong Yu

Zero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively.

Multi-Task Learning

A Survey of Adversarial Learning on Graphs

2 code implementations10 Mar 2020 Liang Chen, Jintang Li, Jiaying Peng, Tao Xie, Zengxu Cao, Kun Xu, Xiangnan He, Zibin Zheng, Bingzhe Wu

To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically.

Clustering Graph Clustering +2

On the Role of Conceptualization in Commonsense Knowledge Graph Construction

1 code implementation6 Mar 2020 Mutian He, Yangqiu Song, Kun Xu, Dong Yu

Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs as they consist of much larger number of nodes formed by loosely-structured text, which, though, enables them to handle highly diverse queries in natural language related to commonsense, leads to unique challenges for automatic KG construction methods.

graph construction Knowledge Graphs +1

Boosting Adversarial Training with Hypersphere Embedding

1 code implementation NeurIPS 2020 Tianyu Pang, Xiao Yang, Yinpeng Dong, Kun Xu, Jun Zhu, Hang Su

Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models.

Representation Learning

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

no code implementations23 Jan 2020 Kun Xu, Linfeng Song, Yansong Feng, Yan Song, Dong Yu

Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity.

Entity Alignment

Multiplex Word Embeddings for Selectional Preference Acquisition

1 code implementation IJCNLP 2019 Hongming Zhang, Jiaxin Bai, Yan Song, Kun Xu, Changlong Yu, Yangqiu Song, Wilfred Ng, Dong Yu

Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words.

Word Embeddings Word Similarity

Triple Generative Adversarial Networks

1 code implementation20 Dec 2019 Chongxuan Li, Kun Xu, Jiashuo Liu, Jun Zhu, Bo Zhang

It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).

Classification Conditional Image Generation +4

Efficient Global String Kernel with Random Features: Beyond Counting Substructures

no code implementations25 Nov 2019 Lingfei Wu, Ian En-Hsu Yen, Siyu Huo, Liang Zhao, Kun Xu, Liang Ma, Shouling Ji, Charu Aggarwal

In this paper, we present a new class of global string kernels that aims to (i) discover global properties hidden in the strings through global alignments, (ii) maintain positive-definiteness of the kernel, without introducing a diagonal dominant kernel matrix, and (iii) have a training cost linear with respect to not only the length of the string but also the number of training string samples.

Understanding and Stabilizing GANs' Training Dynamics with Control Theory

1 code implementation29 Sep 2019 Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang

There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.

Ranked #37 on Image Generation on CIFAR-10 (Inception score metric)

Image Generation L2 Regularization

Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

1 code implementation ICLR 2020 Tianyu Pang, Kun Xu, Jun Zhu

Our experiments on CIFAR-10 and CIFAR-100 demonstrate that MI can further improve the adversarial robustness for the models trained by mixup and its variants.

Adversarial Robustness

DurIAN: Duration Informed Attention Network For Multimodal Synthesis

4 code implementations4 Sep 2019 Chengzhu Yu, Heng Lu, Na Hu, Meng Yu, Chao Weng, Kun Xu, Peng Liu, Deyi Tuo, Shiyin Kang, Guangzhi Lei, Dan Su, Dong Yu

In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously.

Speech Synthesis

Efficient training and design of photonic neural network through neuroevolution

no code implementations4 Aug 2019 Tian Zhang, Jia Wang, Yihang Dan, Yuxiang Lanqiu, Jian Dai, Xu Han, Xiaojuan Sun, Kun Xu

Recently, optical neural networks (ONNs) integrated in photonic chips has received extensive attention because they are expected to implement the same pattern recognition tasks in the electronic platforms with high efficiency and low power consumption.

Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering

no code implementations NAACL 2019 Kun Xu, Yuxuan Lai, Yansong Feng, Zhiguo Wang

However, extending KV-MemNNs to Knowledge Based Question Answering (KB-QA) is not trivia, which should properly decompose a complex question into a sequence of queries against the memory, and update the query representations to support multi-hop reasoning over the memory.

Question Answering Reading Comprehension +1

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

1 code implementation ACL 2019 Kun Xu, Li-Wei Wang, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, Dong Yu

Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.

Entity Embeddings Graph Attention +1

Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness

2 code implementations ICLR 2020 Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e. g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models.

Adversarial Robustness

Lattice CNNs for Matching Based Chinese Question Answering

1 code implementation25 Feb 2019 Yuxuan Lai, Yansong Feng, Xiaohan Yu, Zheng Wang, Kun Xu, Dongyan Zhao

Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly.

Question Answering Text Matching

Improving Adversarial Robustness via Promoting Ensemble Diversity

6 code implementations25 Jan 2019 Tianyu Pang, Kun Xu, Chao Du, Ning Chen, Jun Zhu

Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks.

Adversarial Robustness

To Relieve Your Headache of Training an MRF, Take AdVIL

no code implementations ICLR 2020 Chongxuan Li, Chao Du, Kun Xu, Max Welling, Jun Zhu, Bo Zhang

We propose a black-box algorithm called {\it Adversarial Variational Inference and Learning} (AdVIL) to perform inference and learning on a general Markov random field (MRF).

Variational Inference

From Node Embedding to Graph Embedding: Scalable Global Graph Kernel via Random Features

no code implementations NIPS 2018 2018 Lingfei Wu, Ian En-Hsu Yen, Kun Xu, Liang Zhao, Yinglong Xia, Michael Witbrock

Graph kernels are one of the most important methods for graph data analysis and have been successfully applied in diverse applications.

Graph Embedding

Word Mover's Embedding: From Word2Vec to Document Embedding

1 code implementation EMNLP 2018 Lingfei Wu, Ian E. H. Yen, Kun Xu, Fangli Xu, Avinash Balakrishnan, Pin-Yu Chen, Pradeep Ravikumar, Michael J. Witbrock

While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings.

Document Embedding General Classification +6

SQL-to-Text Generation with Graph-to-Sequence Model

1 code implementation EMNLP 2018 Kun Xu, Lingfei Wu, Zhiguo Wang, Yansong Feng, Vadim Sheinin

Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query.

Graph-to-Sequence SQL-to-Text +1

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

1 code implementation EMNLP 2018 Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Li-Wei Chen, Vadim Sheinin

Existing neural semantic parsers mainly utilize a sequence encoder, i. e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees.

Graph-to-Sequence Semantic Parsing

Deep Structured Generative Models

no code implementations10 Jul 2018 Kun Xu, Haoyu Liang, Jun Zhu, Hang Su, Bo Zhang

Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures.

Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

4 code implementations ICLR 2019 Kun Xu, Lingfei Wu, Zhiguo Wang, Yansong Feng, Michael Witbrock, Vadim Sheinin

Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings.

Graph-to-Sequence SQL-to-Text +1

Chinese Text in the Wild

5 code implementations28 Feb 2018 Tai-Ling Yuan, Zhe Zhu, Kun Xu, Cheng-Jun Li, Shi-Min Hu

[python3. 6] 运用tf实现自然场景文字检测, keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

Optical Character Recognition (OCR)

Fifth order finite volume WENO in general orthogonally-curvilinear coordinates

1 code implementation16 Nov 2017 Mohammad Afzal Shadab, Dinshaw Balsara, Wei Shyy, Kun Xu

A scheme for calculating the linear weights, optimal weights, and smoothness indicator on a regularly- and irregularly-spaced grid in orthogonally-curvilinear coordinates is proposed.

Computational Physics

The YouTube-8M Kaggle Competition: Challenges and Methods

1 code implementation28 Jun 2017 Haosheng Zou, Kun Xu, Jialian Li, Jun Zhu

We took part in the YouTube-8M Video Understanding Challenge hosted on Kaggle, and achieved the 10th place within less than one month's time.

General Classification Video Classification +1

Triple Generative Adversarial Nets

1 code implementation NeurIPS 2017 Chongxuan Li, Kun Xu, Jun Zhu, Bo Zhang

Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL).

Image Generation

Hybrid Question Answering over Knowledge Base and Free Text

no code implementations COLING 2016 Kun Xu, Yansong Feng, Songfang Huang, Dongyan Zhao

While these systems are able to provide more precise answers than information retrieval (IR) based QA systems, the natural incompleteness of KB inevitably limits the question scope that the system can answer.

Information Retrieval Question Answering +2

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