Search Results for author: Wei Xu

Found 216 papers, 87 papers with code

WIKIBIAS: Detecting Multi-Span Subjective Biases in Language

1 code implementation Findings (EMNLP) 2021 Yang Zhong, Jingfeng Yang, Wei Xu, Diyi Yang

Biases continue to be prevalent in modern text and media, especially subjective bias – a special type of bias that introduces improper attitudes or presents a statement with the presupposition of truth.

Sentence

CT-Bound: Fast Boundary Estimation From Noisy Images Via Hybrid Convolution and Transformer Neural Networks

1 code implementation25 Mar 2024 Wei Xu, Junjie Luo, Qi Guo

We present CT-Bound, a fast boundary estimation method for noisy images using a hybrid Convolution and Transformer neural network.

DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation

no code implementations20 Mar 2024 Yifan Wu, Jiawei Du, Ping Liu, Yuewei Lin, Wenqing Cheng, Wei Xu

Dataset distillation is an advanced technique aimed at compressing datasets into significantly smaller counterparts, while preserving formidable training performance.

Adversarial Attack Adversarial Robustness

Knowledge Conflicts for LLMs: A Survey

no code implementations13 Mar 2024 Rongwu Xu, Zehan Qi, Cunxiang Wang, Hongru Wang, Yue Zhang, Wei Xu

This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge.

Misinformation

RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems

1 code implementation11 Mar 2024 Jianxun Lian, Yuxuan Lei, Xu Huang, Jing Yao, Wei Xu, Xing Xie

This paper introduces RecAI, a practical toolkit designed to augment or even revolutionize recommender systems with the advanced capabilities of Large Language Models (LLMs).

Recommendation Systems

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

1 code implementation3 Mar 2024 Xin Zhou, Dingkang Liang, Wei Xu, Xingkui Zhu, Yihan Xu, Zhikang Zou, Xiang Bai

To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task.

Transfer Learning

ELA: Efficient Local Attention for Deep Convolutional Neural Networks

no code implementations2 Mar 2024 Wei Xu, Yi Wan

The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks.

Dimensionality Reduction Image Classification +2

NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms

no code implementations19 Feb 2024 Jonathan Zheng, Alan Ritter, Wei Xu

The performance of Large Language Models (LLMs) degrades from the temporal drift between data used for model training and newer text seen during inference.

Machine Translation Natural Language Understanding +1

PointMamba: A Simple State Space Model for Point Cloud Analysis

1 code implementation16 Feb 2024 Dingkang Liang, Xin Zhou, Xinyu Wang, Xingkui Zhu, Wei Xu, Zhikang Zou, Xiaoqing Ye, Xiang Bai

Recently, state space models (SSM), a new family of deep sequence models, have presented great potential for sequence modeling in NLP tasks.

Digital versus Analog Transmissions for Federated Learning over Wireless Networks

no code implementations15 Feb 2024 Jiacheng Yao, Wei Xu, Zhaohui Yang, Xiaohu You, Mehdi Bennis, H. Vincent Poor

In this paper, we quantitatively compare these two effective communication schemes, i. e., digital and analog ones, for wireless federated learning (FL) over resource-constrained networks, highlighting their essential differences as well as their respective application scenarios.

Federated Learning

Bayesian Federated Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing

no code implementations12 Feb 2024 Wei Xu, An Liu, Yiting Zhang, Vincent Lau

In this work, we propose a message passing based Bayesian federated learning (BFL) framework to avoid these drawbacks. Specifically, we formulate the problem of deep neural network (DNN) learning and compression and as a sparse Bayesian inference problem, in which group sparse prior is employed to achieve structured model compression.

Bayesian Inference Federated Learning +3

Non-autoregressive Generative Models for Reranking Recommendation

no code implementations10 Feb 2024 Yuxin Ren, Qiya Yang, Yichun Wu, Wei Xu, Yalong Wang, Zhiqiang Zhang

Hence, we propose a Non-AutoRegressive generative model for reranking Recommendation (NAR4Rec) designed to enhance efficiency and effectiveness.

Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation

no code implementations6 Feb 2024 Anton Lavrouk, Ian Ligon, Tarek Naous, Jonathan Zheng, Alan Ritter, Wei Xu

The Stanceosaurus corpus (Zheng et al., 2022) was designed to provide high-quality, annotated, 5-way stance data extracted from Twitter, suitable for analyzing cross-cultural and cross-lingual misinformation.

Misinformation Stance Classification +1

Constrained Decoding for Cross-lingual Label Projection

1 code implementation5 Feb 2024 Duong Minh Le, Yang Chen, Alan Ritter, Wei Xu

Therefore, it is common to exploit translation and label projection to further improve the performance by (1) translating training data that is available in a high-resource language (e. g., English) together with the gold labels into low-resource languages, and/or (2) translating test data in low-resource languages to a high-source language to run inference on, then projecting the predicted span-level labels back onto the original test data.

Event Argument Extraction named-entity-recognition +5

Spin: An Efficient Secure Computation Framework with GPU Acceleration

no code implementations4 Feb 2024 Wuxuan Jiang, Xiangjun Song, Shenbai Hong, Haijun Zhang, Wenxin Liu, Bo Zhao, Wei Xu, Yi Li

Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks.

Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks

no code implementations21 Jan 2024 Xihaier Luo, Wei Xu, Yihui Ren, Shinjae Yoo, Balu Nadiga

Reliably reconstructing physical fields from sparse sensor data is a challenge that frequently arises in many scientific domains.

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

1 code implementation20 Jan 2024 Haonan Yu, Wei Xu

Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation.

Object Optical Flow Estimation

Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance

1 code implementation4 Jan 2024 Jiacheng Wang, Ping Liu, Wei Xu

Existing text-to-image editing methods tend to excel either in rigid or non-rigid editing but encounter challenges when combining both, resulting in misaligned outputs with the provided text prompts.

Group Multi-View Transformer for 3D Shape Analysis with Spatial Encoding

no code implementations27 Dec 2023 Lixiang Xu, Qingzhe Cui, Richang Hong, Wei Xu, Enhong Chen, Xin Yuan, Chenglong Li, Yuanyan Tang

The large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB.

3D Classification 3D Shape Recognition +2

Convergence of Heavy-Tailed Hawkes Processes and the Microstructure of Rough Volatility

no code implementations14 Dec 2023 Ulrich Horst, Wei Xu, Rouyi Zhang

We establish the weak convergence of the intensity of a nearly-unstable Hawkes process with heavy-tailed kernel.

The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation

no code implementations14 Dec 2023 Rongwu Xu, Brian S. Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi, Tianwei Zhang, Zhixuan Fang, Wei Xu, Han Qiu

Therefore, in this study, we delve into LLMs' susceptibility to persuasive conversations, particularly on factual questions that they can answer correctly.

Misinformation

Wireless Network Digital Twin for 6G: Generative AI as A Key Enabler

no code implementations29 Nov 2023 Zhenyu Tao, Wei Xu, Yongming Huang, XiaoYun Wang, Xiaohu You

Digital twin, which enables emulation, evaluation, and optimization of physical entities through synchronized digital replicas, has gained increasingly attention as a promising technology for intricate wireless networks.

An HCAI Methodological Framework: Putting It Into Action to Enable Human-Centered AI

no code implementations27 Nov 2023 Wei Xu, Zaifeng Gao, Marvin Dainoff

This paper also presents a "three-layer" approach to facilitate the implementation of the framework.

Philosophy

Reducing Privacy Risks in Online Self-Disclosures with Language Models

no code implementations16 Nov 2023 Yao Dou, Isadora Krsek, Tarek Naous, Anubha Kabra, Sauvik Das, Alan Ritter, Wei Xu

Motivated by the user feedback, we introduce the task of self-disclosure abstraction, which is paraphrasing disclosures into less specific terms while preserving their utility, e. g., "Im 16F" to "I'm a teenage girl".

Language Modelling

Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations

no code implementations16 Nov 2023 Jing Yao, Wei Xu, Jianxun Lian, Xiting Wang, Xiaoyuan Yi, Xing Xie

In this paper, we propose a general paradigm that augments LLMs with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE.

Collaborative Filtering Recommendation Systems +1

Enabling Human-Centered AI: A Methodological Perspective

no code implementations12 Nov 2023 Wei Xu, Zaifeng Gao

Human-centered AI (HCAI) is a design philosophy that advocates prioritizing humans in designing, developing, and deploying intelligent systems, aiming to maximize the benefits of AI to humans and avoid potential adverse impacts.

Philosophy

From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers

1 code implementation18 Oct 2023 Shaoxiong Duan, Yining Shi, Wei Xu

In this paper, we investigate the inherent capabilities of transformer models in learning arithmetic algorithms, such as addition and parity.

Position

Towards Foundation Models for Learning on Tabular Data

no code implementations11 Oct 2023 Han Zhang, Xumeng Wen, Shun Zheng, Wei Xu, Jiang Bian

Despite considerable efforts in developing effective learning models for tabular data, current transferable tabular models remain in their infancy, limited by either the lack of support for direct instruction following in new tasks or the neglect of acquiring foundational knowledge and capabilities from diverse tabular datasets.

Instruction Following Language Modelling +1

Accurate battery lifetime prediction across diverse aging conditions with deep learning

no code implementations8 Oct 2023 Han Zhang, Yuqi Li, Shun Zheng, Ziheng Lu, Xiaofan Gui, Wei Xu, Jiang Bian

Here we introduce a universal deep learning approach that is capable of accommodating various aging conditions and facilitating effective learning under low-resource conditions by leveraging data from rich conditions.

Single-cell modeling

Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network

no code implementations7 Oct 2023 Zhenyu Tao, Wei Xu, Xiaohu You

The proliferation of diverse wireless services in 5G and beyond has led to the emergence of network slicing technologies.

Decision Making Q-Learning

Automatic and Human-AI Interactive Text Generation

no code implementations5 Oct 2023 Yao Dou, Philippe Laban, Claire Gardent, Wei Xu

In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e. g., readability or linguistic styles), while largely retaining the original meaning and the length of the text.

Paraphrase Generation Style Transfer +2

Can Language Models be Instructed to Protect Personal Information?

no code implementations3 Oct 2023 Yang Chen, Ethan Mendes, Sauvik Das, Wei Xu, Alan Ritter

While data leaks should be prevented, it is also crucial to examine the trade-off between the privacy protection and model utility of proposed approaches.

Adversarial Robustness

Agent Teaming Situation Awareness (ATSA): A Situation Awareness Framework for Human-AI Teaming

no code implementations31 Aug 2023 Qi Gao, Wei Xu, Mowei Shen, Zaifeng Gao

To this end, we provide a review of leading SA theoretical models and a new framework for SA in the HAT context based on the key features and processes of HAT.

Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation

1 code implementation14 Aug 2023 David Heineman, Yao Dou, Wei Xu

Additionally, we introduce a Python library to streamline the entire process from typology design and deployment to annotation processing.

Machine Translation Multi-Task Learning +1

Robust MIMO Detection With Imperfect CSI: A Neural Network Solution

no code implementations24 Jul 2023 Yi Sun, Hong Shen, Wei Xu, Nan Hu, Chunming Zhao

Furthermore, a robust detection network RADMMNet is constructed by unfolding the ADMM iterations and employing both model-driven and data-driven philosophies.

Applying HCAI in developing effective human-AI teaming: A perspective from human-AI joint cognitive systems

no code implementations8 Jul 2023 Wei Xu, Zaifeng Gao

Insights: AI has led to the emergence of a new form of human-machine relationship: human-AI teaming (HAT), a paradigmatic shift in human-AI systems; We must follow a human-centered AI (HCAI) approach when applying HAT as a new design paradigm; We propose a conceptual framework of human-AI joint cognitive systems (HAIJCS) to represent and implement HAT for developing effective human-AI teaming

Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning

no code implementations5 Jun 2023 Yao Tang, Guangxu Zhu, Wei Xu, Man Hon Cheung, Tat-Ming Lok, Shuguang Cui

Unmanned Aerial Vehicle (UAV)-mounted edge devices are particularly advantageous for FEEL due to their flexibility and mobility in efficient data collection.

Position Privacy Preserving

Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework

no code implementations2 Jun 2023 Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka

In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting.

reinforcement-learning Transfer Reinforcement Learning

ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models

no code implementations30 May 2023 Huahui Yi, Ziyuan Qin, Wei Xu, Miaotian Guo, Kun Wang, Shaoting Zhang, Kang Li, Qicheng Lao

To achieve this, we propose a Concept Embedding Search (ConES) approach by optimizing prompt embeddings -- without the need of the text encoder -- to capture the 'concept' of the image modality through a variety of task objectives.

Instance Segmentation Prompt Engineering +2

Improved Instruction Ordering in Recipe-Grounded Conversation

1 code implementation26 May 2023 Duong Minh Le, Ruohao Guo, Wei Xu, Alan Ritter

In this paper, we study the task of instructional dialogue and focus on the cooking domain.

Intent Detection Response Generation

Revisiting non-English Text Simplification: A Unified Multilingual Benchmark

1 code implementation25 May 2023 Michael J. Ryan, Tarek Naous, Wei Xu

However, less work has been done on multilingual text simplification due to the lack of a diverse evaluation benchmark that covers complex-simple sentence pairs in many languages.

Sentence Text Simplification +1

Having Beer after Prayer? Measuring Cultural Bias in Large Language Models

no code implementations23 May 2023 Tarek Naous, Michael J. Ryan, Alan Ritter, Wei Xu

In this paper, we show that multilingual and Arabic monolingual LMs exhibit bias towards entities associated with Western culture.

named-entity-recognition Named Entity Recognition +4

Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA

no code implementations23 May 2023 David Heineman, Yao Dou, Mounica Maddela, Wei Xu

Large language models (e. g., GPT-4) are uniquely capable of producing highly rated text simplification, yet current human evaluation methods fail to provide a clear understanding of systems' specific strengths and weaknesses.

Sentence Text Simplification

ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment

1 code implementation23 May 2023 Tarek Naous, Michael J. Ryan, Anton Lavrouk, Mohit Chandra, Wei Xu

We present a systematic study and comprehensive evaluation of large language models for automatic multilingual readability assessment.

Benchmarking Cross-Lingual Transfer +1

Teaching the Pre-trained Model to Generate Simple Texts for Text Simplification

1 code implementation21 May 2023 Renliang Sun, Wei Xu, Xiaojun Wan

In this paper, we propose a new continued pre-training strategy to teach the pre-trained model to generate simple texts.

Lexical Simplification Sentence +1

Multilingual Simplification of Medical Texts

1 code implementation21 May 2023 Sebastian Joseph, Kathryn Kazanas, Keziah Reina, Vishnesh J. Ramanathan, Wei Xu, Byron C. Wallace, Junyi Jessy Li

This work addresses this limitation via multilingual simplification, i. e., directly simplifying complex texts into simplified texts in multiple languages.

Sentence Text Simplification

Semantic-aware Digital Twin for Metaverse: A Comprehensive Review

no code implementations12 May 2023 Senthil Kumar Jagatheesaperumal, Zhaohui Yang, Qianqian Yang, Chongwen Huang, Wei Xu, Mohammad Shikh-Bahaei, Zhaoyang Zhang

To facilitate the deployment of digital twins in Metaverse, the paradigm with semantic awareness has been proposed as a means for enabling accurate and task-oriented information extraction with inherent intelligence.

Management

Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models

no code implementations2 May 2023 Junmo Kang, Wei Xu, Alan Ritter

Fine-tuning large models is highly effective, however, inference can be expensive and produces carbon emissions.

Knowledge Distillation

Self-information Domain-based Neural CSI Compression with Feature Coupling

no code implementations30 Apr 2023 Ziqing Yin, Renjie Xie, Wei Xu, Zhaohui Yang, Xiaohu You

The proposed SD-CsiNet projects the raw CSI onto a self-information matrix in the newly-defined self-information domain, extracts both temporal and spatial features of the self-information matrix, and then couples these two features for effective compression.

Text-guided Eyeglasses Manipulation with Spatial Constraints

no code implementations25 Apr 2023 Jiacheng Wang, Ping Liu, Jingen Liu, Wei Xu

To address these limitations, we propose a Text-guided Eyeglasses Manipulation method that allows for control of the eyeglasses shape and style based on a binary mask and text, respectively.

Virtual Try-on

Super-Resolution Information Enhancement For Crowd Counting

1 code implementation13 Mar 2023 Jiahao Xie, Wei Xu, Dingkang Liang, Zhanyu Ma, Kongming Liang, Weidong Liu, Rui Wang, Ling Jin

As the proposed method requires SR labels, we further propose a Super-Resolution Crowd Counting dataset (SR-Crowd).

Crowd Counting Super-Resolution

Towards General Purpose Medical AI: Continual Learning Medical Foundation Model

no code implementations12 Mar 2023 Huahui Yi, Ziyuan Qin, Qicheng Lao, Wei Xu, Zekun Jiang, Dequan Wang, Shaoting Zhang, Kang Li

Therefore, in this work, we further explore the possibility of leveraging pre-trained VLMs as medical foundation models for building general-purpose medical AI, where we thoroughly investigate three machine-learning paradigms, i. e., domain/task-specialized learning, joint learning, and continual learning, for training the VLMs and evaluate their generalization performance on cross-domain and cross-task test sets.

Continual Learning

User-Centered Design (IX): A "User Experience 3.0" Paradigm Framework in the Intelligence Era

no code implementations13 Feb 2023 Wei Xu

The proposal of the "UX 3. 0" paradigm helps improve the existing UX methods and provides methodological support for the research and applications of UX in developing intelligent systems.

Philosophy

Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective

no code implementations25 Jan 2023 Jiayuan Chen, Xiang Zhang, Yinfei Xu, Tianli Zhao, Renjie Xie, Wei Xu

Given the fixed point equation (FPE) derived from the variational inference on the Markov random fields, the deep GNNs, including JKNet, GCNII, DGCN, and the classical GNNs, such as GCN, GAT, and APPNP, can be regarded as different approximations of the FPE.

Variational Inference

AI in HCI Design and User Experience

no code implementations3 Jan 2023 Wei Xu

We then discuss how AI technology can be used to enhance HCI/UX design.

Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients

no code implementations ICCV 2023 Wenshuo Ma, Yidong Li, Xiaofeng Jia, Wei Xu

Visual Transformers (ViTs) and Convolutional Neural Networks (CNNs) are the two primary backbone structures extensively used in various vision tasks.

Adversarial Attack

LENS: A Learnable Evaluation Metric for Text Simplification

1 code implementation19 Dec 2022 Mounica Maddela, Yao Dou, David Heineman, Wei Xu

Training learnable metrics using modern language models has recently emerged as a promising method for the automatic evaluation of machine translation.

Machine Translation Text Simplification

Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments

1 code implementation19 Dec 2022 Ethan Mendes, Yang Chen, Wei Xu, Alan Ritter

We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that support them.

Fact Checking Misinformation

Frustratingly Easy Label Projection for Cross-lingual Transfer

1 code implementation28 Nov 2022 Yang Chen, Chao Jiang, Alan Ritter, Wei Xu

Translating training data into many languages has emerged as a practical solution for improving cross-lingual transfer.

Cross-Lingual NER NER +4

Stanceosaurus: Classifying Stance Towards Multilingual Misinformation

no code implementations28 Oct 2022 Jonathan Zheng, Ashutosh Baheti, Tarek Naous, Wei Xu, Alan Ritter

We present Stanceosaurus, a new corpus of 28, 033 tweets in English, Hindi, and Arabic annotated with stance towards 251 misinformation claims.

Domain Adaptation Fact Checking +1

arXivEdits: Understanding the Human Revision Process in Scientific Writing

no code implementations26 Oct 2022 Chao Jiang, Wei Xu, Samuel Stevens

We first introduce arXivEdits, a new annotated corpus of 751 full papers from arXiv with gold sentence alignment across their multiple versions of revision, as well as fine-grained span-level edits and their underlying intentions for 1, 000 sentence pairs.

intent-classification Intent Classification +1

PaCo: Parameter-Compositional Multi-Task Reinforcement Learning

1 code implementation21 Oct 2022 Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka

However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing.

reinforcement-learning Reinforcement Learning (RL)

Improving Large-scale Paraphrase Acquisition and Generation

no code implementations6 Oct 2022 Yao Dou, Chao Jiang, Wei Xu

This paper addresses the quality issues in existing Twitter-based paraphrase datasets, and discusses the necessity of using two separate definitions of paraphrase for identification and generation tasks.

Language Modelling Paraphrase Generation +2

A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting

1 code implementation17 Aug 2022 Pradyumna Tambwekar, Lakshita Dodeja, Nathan Vaska, Wei Xu, Matthew Gombolay

Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i. e., goals and constraints) from language (p < 0. 05).

Machine Translation

Intelligent MIMO Detection Using Meta Learning

no code implementations8 Aug 2022 Haomiao Huo, Jindan Xu, Gege Su, Wei Xu, Ning Wang

By treating K as a variable that can be adjusted according to a fitting function of some learnable coefficients, an intelligent MIMO detection network based on deep neural networks (DNN) is proposed to reduce complexity of the detection algorithm with little performance degradation.

Meta-Learning

Disentangled Representation Learning for RF Fingerprint Extraction under Unknown Channel Statistics

1 code implementation4 Aug 2022 Renjie Xie, Wei Xu, Jiabao Yu, Aiqun Hu, Derrick Wing Kwan Ng, A. Lee Swindlehurst

Deep learning (DL) applied to a device's radio-frequency fingerprint~(RFF) has attracted significant attention in physical-layer authentication due to its extraordinary classification performance.

Data Augmentation Representation Learning

Semi-supervised MIMO Detection Using Cycle-consistent Generative Adversarial Network

no code implementations8 Jun 2022 Hongzhi Zhu, Yongliang Guo, Wei Xu, Xiaohu You

In this paper, a new semi-supervised deep multiple-input multiple-output (MIMO) detection approach using a cycle-consistent generative adversarial network (CycleGAN) is proposed for communication systems without any prior knowledge of underlying channel distributions.

Generative Adversarial Network

HMRNet: High and Multi-Resolution Network with Bidirectional Feature Calibration for Brain Structure Segmentation in Radiotherapy

1 code implementation7 Jun 2022 Hao Fu, Guotai Wang, Wenhui Lei, Wei Xu, Qianfei Zhao, Shichuan Zhang, Kang Li, Shaoting Zhang

Accurate segmentation of Anatomical brain Barriers to Cancer spread (ABCs) plays an important role for automatic delineation of Clinical Target Volume (CTV) of brain tumors in radiotherapy.

Segmentation

Learning to Optimize Resource Assignment for Task Offloading in Mobile Edge Computing

no code implementations15 Mar 2022 Yurong Qian, Jindan Xu, Shuhan Zhu, Wei Xu, Lisheng Fan, George K. Karagiannidis

In this paper, we consider a multiuser mobile edge computing (MEC) system, where a mixed-integer offloading strategy is used to assist the resource assignment for task offloading.

Edge-computing

An End-to-End Transformer Model for Crowd Localization

1 code implementation26 Feb 2022 Dingkang Liang, Wei Xu, Xiang Bai

Crowd localization, predicting head positions, is a more practical and high-level task than simply counting.

A Bayesian Deep Learning Approach to Near-Term Climate Prediction

no code implementations23 Feb 2022 Xihaier Luo, Balasubramanya T. Nadiga, Yihui Ren, Ji Hwan Park, Wei Xu, Shinjae Yoo

Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction.

A Geometric Understanding of Natural Gradient

no code implementations13 Feb 2022 Qinxun Bai, Steven Rosenberg, Wei Xu

While natural gradients have been widely studied from both theoretical and empirical perspectives, we argue that some fundamental theoretical issues regarding the existence of gradients in infinite dimensional function spaces remain underexplored.

Do You Need the Entropy Reward (in Practice)?

2 code implementations28 Jan 2022 Haonan Yu, Haichao Zhang, Wei Xu

On the other hand, our large-scale empirical study shows that using entropy regularization alone in policy improvement, leads to comparable or even better performance and robustness than using it in both policy improvement and policy evaluation.

Towards Safe Reinforcement Learning with a Safety Editor Policy

1 code implementation28 Jan 2022 Haonan Yu, Wei Xu, Haichao Zhang

On 12 Safety Gym tasks and 2 safe racing tasks, SEditor obtains much a higher overall safety-weighted-utility (SWU) score than the baselines, and demonstrates outstanding utility performance with constraint violation rates as low as once per 2k time steps, even in obstacle-dense environments.

reinforcement-learning Reinforcement Learning (RL) +1

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

1 code implementation ICLR 2022 Haichao Zhang, Wei Xu, Haonan Yu

GPM can therefore leverage its generated multi-step plans for temporally coordinated exploration towards high value regions, which is potentially more effective than a sequence of actions generated by perturbing each action at single step level, whose consistent movement decays exponentially with the number of exploration steps.

reinforcement-learning Reinforcement Learning (RL)

User Centered Design (VI): Human Factors Approaches for Intelligent Human-Computer Interaction

no code implementations8 Nov 2021 Wei Xu

With the help of the concept and framework, the paper analyzes the human factors issues in the ecosystem of autonomous vehicle co-driving and proposes an initial human factors solution.

Intent Detection Philosophy

Natural Language for Human-Robot Collaboration: Problems Beyond Language Grounding

no code implementations9 Oct 2021 Seth Pate, Wei Xu, ZiYi Yang, Maxwell Love, Siddarth Ganguri, Lawson L. S. Wong

To enable robots to instruct humans in collaborations, we identify several aspects of language processing that are not commonly studied in this context.

Faster Reinforcement Learning with Value Target Lower Bounding

no code implementations29 Sep 2021 Le Zhao, Wei Xu

In practice, discounted episodic return from the training experience or discounted goal return from hindsight relabeling can serve as the value lower bound when the environment is deterministic.

Atari Games Continuous Control +2

BiSECT: Learning to Split and Rephrase Sentences with Bitexts

1 code implementation EMNLP 2021 Joongwon Kim, Mounica Maddela, Reno Kriz, Wei Xu, Chris Callison-Burch

We categorize examples in our corpus, and use these categories in a novel model that allows us to target specific regions of the input sentence to be split and edited.

Machine Translation Sentence +2

Pre-train or Annotate? Domain Adaptation with a Constrained Budget

1 code implementation EMNLP 2021 Fan Bai, Alan Ritter, Wei Xu

Our experiments suggest task-specific data annotation should be part of an economical strategy when adapting an NLP model to a new domain.

Domain Adaptation

Feature Importance in a Deep Learning Climate Emulator

no code implementations27 Aug 2021 Wei Xu, Xihaier Luo, Yihui Ren, Ji Hwan Park, Shinjae Yoo, Balasubramanya T. Nadiga

From the perspective of climate dynamics, these findings suggest a dominant role for local processes and a negligible role for remote teleconnections at the spatial and temporal scales we consider.

Feature Importance

Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need

1 code implementation20 Aug 2021 Zhengyi Ma, Zhicheng Dou, Wei Xu, Xinyu Zhang, Hao Jiang, Zhao Cao, Ji-Rong Wen

In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval.

Language Modelling Retrieval

A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication

1 code implementation10 Aug 2021 Renjie Xie, Wei Xu, Yanzhi Chen, Jiabao Yu, Aiqun Hu, Derrick Wing Kwan Ng, A. Lee Swindlehurst

To enable the discrimination of RFF from both known and unknown devices, we propose a new end-to-end deep learning framework for extracting RFFs from raw received signals.

Inductive Bias

Neural semi-Markov CRF for Monolingual Word Alignment

1 code implementation ACL 2021 Wuwei Lan, Chao Jiang, Wei Xu

Monolingual word alignment is important for studying fine-grained editing operations (i. e., deletion, addition, and substitution) in text-to-text generation tasks, such as paraphrase generation, text simplification, neutralizing biased language, etc.

Paraphrase Generation Sentence +3

Transitioning to human interaction with AI systems: New challenges and opportunities for HCI professionals to enable human-centered AI

no code implementations12 May 2021 Wei Xu, Marvin J. Dainoff, Liezhong Ge, Zaifeng Gao

We propose alternative methods that can help overcome these limitations and effectively help HCI professionals apply the HCAI approach to the development of AI systems.

Super Solutions of the Model RB

no code implementations9 May 2021 Guangyan Zhou, Wei Xu

The concept of super solution is a special type of generalized solutions with certain degree of robustness and stability.

TransCrowd: weakly-supervised crowd counting with transformers

1 code implementation19 Apr 2021 Dingkang Liang, Xiwu Chen, Wei Xu, Yu Zhou, Xiang Bai

Current weakly-supervised counting methods adopt the CNN to regress a total count of the crowd by an image-to-count paradigm.

Crowd Counting

TAAC: Temporally Abstract Actor-Critic for Continuous Control

2 code implementations NeurIPS 2021 Haonan Yu, Wei Xu, Haichao Zhang

TAAC has two important features: a) persistent exploration, and b) a new compare-through Q operator for multi-step TD backup, specially tailored to the action repetition scenario.

Continuous Control

Mutual Information State Intrinsic Control

2 code implementations ICLR 2021 Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu

Reinforcement learning has been shown to be highly successful at many challenging tasks.

Generative Particle Variational Inference via Estimation of Functional Gradients

no code implementations1 Mar 2021 Neale Ratzlaff, Qinxun Bai, Li Fuxin, Wei Xu

Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference.

Variational Inference

R2LIVE: A Robust, Real-time, LiDAR-Inertial-Visual tightly-coupled state Estimator and mapping

1 code implementation24 Feb 2021 Jiarong Lin, Chunran Zheng, Wei Xu, Fu Zhang

Our proposed framework is composed of two parts: the filter-based odometry and factor graph optimization.

Robotics

Focal Inverse Distance Transform Maps for Crowd Localization

3 code implementations16 Feb 2021 Dingkang Liang, Wei Xu, Yingying Zhu, Yu Zhou

Most regression-based methods utilize convolution neural networks (CNN) to regress a density map, which can not accurately locate the instance in the extremely dense scene, attributed to two crucial reasons: 1) the density map consists of a series of blurry Gaussian blobs, 2) severe overlaps exist in the dense region of the density map.

Crowd Counting SSIM

Hierarchical Reinforcement Learning By Discovering Intrinsic Options

1 code implementation ICLR 2021 Jesse Zhang, Haonan Yu, Wei Xu

We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-agnostic options in a self-supervised manner while jointly learning to utilize them to solve sparse-reward tasks.

Hierarchical Reinforcement Learning reinforcement-learning +1

Modeling Heterogeneous Statistical Patterns in High-dimensional Data by Adversarial Distributions: An Unsupervised Generative Framework

1 code implementation15 Dec 2020 Han Zhang, Wenhao Zheng, Charley Chen, Kevin Gao, Yao Hu, Ling Huang, Wei Xu

Meanwhile, such applications usually require modeling the intrinsic clusters in high-dimensional data, which usually displays heterogeneous statistical patterns as the patterns of different clusters may appear in different dimensions.

Anomaly Detection Fraud Detection

FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems

1 code implementation15 Dec 2020 Lu Chen, Jiao Sun, Wei Xu

In both letter-level and word-level attacks, our experiments show that in addition to natural appearance, FAWA achieves a 100% attack success rate with 60% less perturbations and 78% fewer iterations on average.

Optical Character Recognition Optical Character Recognition (OCR)

Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting

no code implementations15 Dec 2020 Wei Xu, Dingkang Liang, Yixiao Zheng, Zhanyu Ma

In this paper, we propose a simple yet efficient counting network based on point-level annotations.

Object Object Counting

Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images

2 code implementations13 Dec 2020 Wenhui Lei, Wei Xu, Ran Gu, Hao Fu, Shaoting Zhang, Guotai Wang

To address this problem, we present a one-shot framework for organ and landmark localization in volumetric medical images, which does not need any annotation during the training stage and could be employed to locate any landmarks or organs in test images given a support (reference) image during the inference stage.

Contrastive Learning Object Localization +4

Controllable Text Simplification with Explicit Paraphrasing

no code implementations NAACL 2021 Mounica Maddela, Fernando Alva-Manchego, Wei Xu

Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting.

Data Augmentation Text Simplification

Sliding Differential Evolution Scheduling for Federated Learning in Bandwidth-Limited Networks

no code implementations18 Oct 2020 Yifan Luo, Jindan Xu, Wei Xu, Kezhi Wang

Federated learning (FL) in a bandwidth-limited network with energy-limited user equipments (UEs) is under-explored.

Federated Learning Scheduling

FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter

2 code implementations16 Oct 2020 Wei Xu, Fu Zhang

To lower the computation load in the presence of large number of measurements, we present a new formula to compute the Kalman gain.

Robotics

An Empowerment-based Solution to Robotic Manipulation Tasks with Sparse Rewards

no code implementations15 Oct 2020 Siyu Dai, Wei Xu, Andreas Hofmann, Brian Williams

In order to provide adaptive and user-friendly solutions to robotic manipulation, it is important that the agent can learn to accomplish tasks even if they are only provided with very sparse instruction signals.

reinforcement-learning Reinforcement Learning (RL)

Robots State Estimation and Observability Analysis Based on Statistical Motion Models

no code implementations12 Oct 2020 Wei Xu, Dongjiao He, Yixi Cai, Fu Zhang

It is shown that this new paradigm is much simpler and more natural than existing methods based on quaternion parameterizations.

POS Translation

Beamforming Design for Multiuser Transmission Through Reconfigurable Intelligent Surface

no code implementations24 Sep 2020 Zhaohui Yang, Wei Xu, Chongwen Huang, Jianfeng Shi, Mohammad Shikh-Bahaei

To solve this problem, a dual method is proposed, where the dual problem is obtained as a semidefinite programming problem.

Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing

no code implementations23 Sep 2020 Liang Wang, Kezhi Wang, Cunhua Pan, Wei Xu, Nauman Aslam, Lajos Hanzo

An unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) framework is proposed, where several UAVs having different trajectories fly over the target area and support the user equipments (UEs) on the ground.

Edge-computing Fairness +1

Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images

no code implementations3 Sep 2020 Xinyi Huang, Suphanut Jamonnak, Ye Zhao, Boyu Wang, Minh Hoai, Kevin Yager, Wei Xu

Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images.

Image Classification

AnciNet: An Efficient Deep Learning Approach for Feedback Compression of Estimated CSI in Massive MIMO Systems

no code implementations17 Aug 2020 Yuyao Sun, Wei Xu, Lisheng Fan, Geoffrey Ye Li, George K. Karagiannidis

Accurate channel state information (CSI) feedback plays a vital role in improving the performance gain of massive multiple-input multiple-output (m-MIMO) systems, where the dilemma is excessive CSI overhead versus limited feedback bandwith.

Analysis and Optimization for RIS-Aided Multi-Pair Communications Relying on Statistical CSI

no code implementations22 Jul 2020 Zhangjie Peng, Tianshu Li, Cunhua Pan, Hong Ren, Wei Xu, Marco Di Renzo

Simulation results verify the correctness of the obtained results and show that the proposed GA method has almost the same performance as the globally optimal solution.

Quantization

Joint Transmit Power and Placement Optimization for URLLC-enabled UAV Relay Systems

no code implementations20 Jul 2020 Hong Ren, Cunhua Pan, Kezhi Wang, Wei Xu, Maged Elkashlan, Arumugam Nallanathan

This letter considers an unmanned aerial vehicle (UAV)-enabled relay communication system for delivering latency-critical messages with ultra-high reliability, where the relay is operating under amplifier-and-forward (AF) mode.

Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network

no code implementations11 Jun 2020 Zeyun Tang, Yongliang Shen, Xinyin Ma, Wei Xu, Jiale Yu, Weiming Lu

Meanwhile, we propose Gated-RGCN to accumulate evidence on the path-based reasoning graph, which contains a new question-aware gating mechanism to regulate the usefulness of information propagating across documents and add question information during reasoning.

Multi-Hop Reading Comprehension

Extracting a Knowledge Base of COVID-19 Events from Social Media

2 code implementations COLING 2022 Shi Zong, Ashutosh Baheti, Wei Xu, Alan Ritter

In this paper, we present a manually annotated corpus of 10, 000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions.

Extracting COVID-19 Events from Twitter slot-filling

Feature Statistics Guided Efficient Filter Pruning

no code implementations21 May 2020 Hang Li, Chen Ma, Wei Xu, Xue Liu

Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications.

Neural CRF Model for Sentence Alignment in Text Simplification

1 code implementation ACL 2020 Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles.

Semantic Similarity Semantic Textual Similarity +2

Code and Named Entity Recognition in StackOverflow

2 code implementations ACL 2020 Jeniya Tabassum, Mounica Maddela, Wei Xu, Alan Ritter

We also present the SoftNER model which achieves an overall 79. 10 F$_1$ score for code and named entity recognition on StackOverflow data.

named-entity-recognition Named Entity Recognition +1

Energy-Efficient Wireless Communications with Distributed Reconfigurable Intelligent Surfaces

no code implementations1 May 2020 Zhaohui Yang, Mingzhe Chen, Walid Saad, Wei Xu, Mohammad Shikh-Bahaei, H. Vincent Poor, Shuguang Cui

In this network, multiple RISs are spatially distributed to serve wireless users and the energy efficiency of the network is maximized by dynamically controlling the on-off status of each RIS as well as optimizing the reflection coefficients matrix of the RISs.

An Empirical Study of Pre-trained Transformers for Arabic Information Extraction

1 code implementation EMNLP 2020 Wuwei Lan, Yang Chen, Wei Xu, Alan Ritter

Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer.

Cross-Lingual Transfer Language Modelling +10

KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion

1 code implementation Findings (ACL) 2021 Jie Zhou, Shengding Hu, Xin Lv, Cheng Yang, Zhiyuan Liu, Wei Xu, Jie Jiang, Juanzi Li, Maosong Sun

Based on the datasets, we propose novel tasks such as multi-hop knowledge abstraction (MKA), multi-hop knowledge concretization (MKC) and then design a comprehensive benchmark.

Knowledge Graphs Transfer Learning

DCMD: Distance-based Classification Using Mixture Distributions on Microbiome Data

no code implementations29 Mar 2020 Konstantin Shestopaloff, Mei Dong, Fan Gao, Wei Xu

The performance of the model is assessed using simulations and applied to a human microbiome study, with results compared against a number of existing machine learning and distance-based approaches.

BIG-bench Machine Learning Classification +1

AI Driven Heterogeneous MEC System with UAV Assistance for Dynamic Environment -- Challenges and Solutions

no code implementations11 Feb 2020 Feibo Jiang, Kezhi Wang, Li Dong, Cunhua Pan, Wei Xu, Kun Yang

By taking full advantage of Computing, Communication and Caching (3C) resources at the network edge, Mobile Edge Computing (MEC) is envisioned as one of the key enablers for the next generation networks.

Decision Making Edge-computing +3

Interpreting Galaxy Deblender GAN from the Discriminator's Perspective

no code implementations17 Jan 2020 Heyi Li, Yuewei Lin, Klaus Mueller, Wei Xu

Using the Galaxy Zoo dataset we demonstrate that our method clearly reveals attention areas of the Discriminator when differentiating generated galaxy images from ground truth images.

Astronomy Data Augmentation

Discourse Level Factors for Sentence Deletion in Text Simplification

no code implementations23 Nov 2019 Yang Zhong, Chao Jiang, Wei Xu, Junyi Jessy Li

We inspect various document and discourse factors associated with sentence deletion, using a new manually annotated sentence alignment corpus we collected.

Sentence Text Simplification

Implicit Generative Modeling for Efficient Exploration

no code implementations ICML 2020 Neale Ratzlaff, Qinxun Bai, Li Fuxin, Wei Xu

Each random draw from our generative model is a neural network that instantiates the dynamic function, hence multiple draws would approximate the posterior, and the variance in the future prediction based on this posterior is used as an intrinsic reward for exploration.

Efficient Exploration Future prediction

Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing

no code implementations10 Nov 2019 Liang Wang, Kezhi Wang, Cunhua Pan, Wei Xu, Nauman Aslam, Arumugam Nallanathan

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user equipment (UE).

Edge-computing reinforcement-learning +1

Generalizing Natural Language Analysis through Span-relation Representations

3 code implementations ACL 2020 Zhengbao Jiang, Wei Xu, Jun Araki, Graham Neubig

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +8

Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images

no code implementations10 Oct 2019 Xinyi Huang, Suphanut Jamonnak, Ye Zhao, Boyu Wang, Minh Hoai, Kevin Yager, Wei Xu

This extended abstract presents a visualization system, which is designed for domain scientists to visually understand their deep learning model of extracting multiple attributes in x-ray scattering images.

Self-Supervised State-Control through Intrinsic Mutual Information Rewards

1 code implementation25 Sep 2019 Rui Zhao, Volker Tresp, Wei Xu

Our results show that the mutual information between the context states and the states of interest can be an effective ingredient for overcoming challenges in robotic manipulation tasks with sparse rewards.

OpenAI Gym reinforcement-learning +1

Bit-level Optimized Neural Network for Multi-antenna Channel Quantization

no code implementations24 Sep 2019 Chao Lu, Wei Xu, Shi Jin, Kezhi Wang

Quantized channel state information (CSI) plays a critical role in precoding design which helps reap the merits of multiple-input multiple-output (MIMO) technology.

Information Theory Signal Processing Information Theory

Acceleration Based Iterative Learning Control for Pugachev's Cobra Maneuver with Quadrotor Tail-sitter VTOL UAVs

no code implementations6 Jun 2019 Wei Xu, Haowei Gu, Fu Zhang

Both the feedback controller and the iterative learning feed-forward controller are based on the aircraft acceleration model, which is directly measurable by the onboard accelerometer.

Systems and Control

Multi-task Pairwise Neural Ranking for Hashtag Segmentation

1 code implementation ACL 2019 Mounica Maddela, Wei Xu, Daniel Preoţiuc-Pietro

Hashtags are often employed on social media and beyond to add metadata to a textual utterance with the goal of increasing discoverability, aiding search, or providing additional semantics.

Segmentation Sentiment Analysis

The ALOS Dataset for Advert Localization in Outdoor Scenes

no code implementations16 Apr 2019 Soumyabrata Dev, Murhaf Hossari, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié

The rapid increase in the number of online videos provides the marketing and advertising agents ample opportunities to reach out to their audience.

BIG-bench Machine Learning Marketing +3

Learning Good Representation via Continuous Attention

no code implementations29 Mar 2019 Liang Zhao, Wei Xu

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation.

Object Object Recognition +2

The CASE Dataset of Candidate Spaces for Advert Implantation

no code implementations21 Mar 2019 Soumyabrata Dev, Murhaf Hossari, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié

With the advent of faster internet services and growth of multimedia content, we observe a massive growth in the number of online videos.

Marketing Semantic Segmentation

RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets

1 code implementation9 Nov 2018 Liping Li, Wei Xu, Tianyi Chen, Georgios B. Giannakis, Qing Ling

In this paper, we propose a class of robust stochastic subgradient methods for distributed learning from heterogeneous datasets at presence of an unknown number of Byzantine workers.

ADNet: A Deep Network for Detecting Adverts

no code implementations9 Nov 2018 Murhaf Hossari, Soumyabrata Dev, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié

Online video advertising gives content providers the ability to deliver compelling content, reach a growing audience, and generate additional revenue from online media.

Detecting Adverts Marketing

DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction

1 code implementation ACL 2019 Shun Zheng, Xu Han, Yankai Lin, Peilin Yu, Lu Chen, Ling Huang, Zhiyuan Liu, Wei Xu

To demonstrate the effectiveness of DIAG-NRE, we apply it to two real-world datasets and present both significant and interpretable improvements over state-of-the-art methods.

Relation Relation Extraction

Zero-Shot Transfer VQA Dataset

no code implementations2 Nov 2018 Yuanpeng Li, Yi Yang, Jian-Yu Wang, Wei Xu

Therefore, toaccelerate this research, we propose a newzero-shot transfer VQA(ZST-VQA)dataset by reorganizing the existing VQA v1. 0 dataset in the way that duringtraining, some words appear only in one module (i. e. questions) but not in theother (i. e. answers).

Question Answering Transfer Learning +1

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

1 code implementation14 Oct 2018 Chenxu Luo, Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia, Alan Yuille

Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods.

Depth Estimation Optical Flow Estimation +2

A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification

1 code implementation EMNLP 2018 Mounica Maddela, Wei Xu

Current lexical simplification approaches rely heavily on heuristics and corpus level features that do not always align with human judgment.

Lexical Simplification

Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos

1 code implementation8 Oct 2018 Yang Wang, Zhenheng Yang, Peng Wang, Yi Yang, Chenxu Luo, Wei Xu

Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.

Motion Estimation Optical Flow Estimation

Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking

no code implementations5 Aug 2018 Han Shen, Lichao Huang, Chang Huang, Wei Xu

The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from learning directly from the feature.

Multi-Object Tracking Multiple Object Tracking +1

Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

no code implementations27 Jun 2018 Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia

The four types of information, i. e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered.

Depth And Camera Motion Optical Flow Estimation +1

Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering

1 code implementation COLING 2018 Wuwei Lan, Wei Xu

In this paper, we analyze several neural network designs (and their variations) for sentence pair modeling and compare their performance extensively across eight datasets, including paraphrase identification, semantic textual similarity, natural language inference, and question answering tasks.

Natural Language Inference Paraphrase Identification +3

Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

1 code implementation22 May 2018 Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu

Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning.

reinforcement-learning Reinforcement Learning (RL) +2

Character-based Neural Networks for Sentence Pair Modeling

1 code implementation NAACL 2018 Wuwei Lan, Wei Xu

Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference.

Natural Language Inference Paraphrase Identification +3

DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map

1 code implementation CVPR 2018 Peng Wang, Ruigang Yang, Binbin Cao, Wei Xu, Yuanqing Lin

The uniqueness of our design is a sensor fusion scheme which integrates camera videos, motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robustness and efficiency of the system.

Autonomous Driving Pose Estimation +2

Scaling Nakamoto Consensus to Thousands of Transactions per Second

1 code implementation10 May 2018 Chenxing Li, Peilun Li, Dong Zhou, Wei Xu, Fan Long

The Conflux consensus protocol represents relationships between blocks as a direct acyclic graph and achieves consensus on a total order of the blocks.

Distributed, Parallel, and Cluster Computing

LEGO: Learning Edge with Geometry all at Once by Watching Videos

1 code implementation CVPR 2018 Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia

In our framework, the predicted depths, normals and edges are forced to be consistent all the time.

Occlusion Aware Unsupervised Learning of Optical Flow

no code implementations CVPR 2018 Yang Wang, Yi Yang, Zhenheng Yang, Liang Zhao, Peng Wang, Wei Xu

Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.

Optical Flow Estimation

Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency

no code implementations10 Nov 2017 Zhenheng Yang, Peng Wang, Wei Xu, Liang Zhao, Ramakant Nevatia

Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years.

Depth Estimation

DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting

1 code implementation27 Sep 2017 Xingyi Cheng, Ruiqing Zhang, Jie zhou, Wei Xu

Several pioneering approaches have been proposed based on traffic observations of the target location as well as its adjacent regions, but they obtain somewhat limited accuracy due to a lack of mining road topology.

From Shakespeare to Twitter: What are Language Styles all about?

no code implementations WS 2017 Wei Xu

As natural language processing research is growing and largely driven by the availability of data, we expanded research from news and small-scale dialog corpora to web and social media.

Lexical Simplification Position +2

A Continuously Growing Dataset of Sentential Paraphrases

no code implementations EMNLP 2017 Wuwei Lan, Siyu Qiu, Hua He, Wei Xu

The main advantage of our method is its simplicity, as it gets rid of the classifier or human in the loop needed to select data before annotation and subsequent application of paraphrase identification algorithms in the previous work.

Benchmarking Paraphrase Identification +1

Listen, Interact and Talk: Learning to Speak via Interaction

1 code implementation28 May 2017 Haichao Zhang, Haonan Yu, Wei Xu

One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language.

Sentence

Unsupervised Learning Layers for Video Analysis

no code implementations24 May 2017 Liang Zhao, Yang Wang, Yi Yang, Wei Xu

This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones.

Object Localization

Dynamic Computational Time for Visual Attention

1 code implementation30 Mar 2017 Zhichao Li, Yi Yang, Xiao Liu, Feng Zhou, Shilei Wen, Wei Xu

We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM).

reinforcement-learning Reinforcement Learning (RL)

A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

no code implementations28 Mar 2017 Haonan Yu, Haichao Zhang, Wei Xu

We believe that our results provide some preliminary insights on how to train an agent with similar abilities in a 3D environment.

Language Acquisition Navigate +1

Discovering Conversational Dependencies between Messages in Dialogs

no code implementations8 Dec 2016 Wenchao Du, Pascal Poupart, Wei Xu

We investigate the task of inferring conversational dependencies between messages in one-on-one online chat, which has become one of the most popular forms of customer service.

Results of the WNUT16 Named Entity Recognition Shared Task

no code implementations WS 2016 Benjamin Strauss, Bethany Toma, Alan Ritter, Marie-Catherine de Marneffe, Wei Xu

This paper presents the results of the Twitter Named Entity Recognition shared task associated with W-NUT 2016: a named entity tagging task with 10 teams participating.

Named Entity Recognition Named Entity Recognition (NER)

Automatically Building Face Datasets of New Domains from Weakly Labeled Data with Pretrained Models

no code implementations24 Nov 2016 Shengyong Ding, Junyu Wu, Wei Xu, Hongyang Chao

In this paper, we propose a method to automatically and incrementally construct datasets from massive weakly labeled data of the target domain which are readily available on the Internet under the help of a pretrained face model.

Face Model Face Recognition

Deep Joint Face Hallucination and Recognition

no code implementations24 Nov 2016 Junyu Wu, Shengyong Ding, Wei Xu, Hongyang Chao

However, we observe that directly feeding the hallucinated facial images into recog- nition models can even degrade the recognition performance despite the much better visualization quality.

Face Hallucination Face Recognition +1

Neural Machine Translation with Pivot Languages

no code implementations15 Nov 2016 Yong Cheng, Yang Liu, Qian Yang, Maosong Sun, Wei Xu

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs.

Machine Translation Translation

TweeTime: A Minimally Supervised Method for Recognizing and Normalizing Time Expressions in Twitter

1 code implementation9 Aug 2016 Jeniya Tabassum, Alan Ritter, Wei Xu

We describe TweeTIME, a temporal tagger for recognizing and normalizing time expressions in Twitter.

Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering

3 code implementations21 Jul 2016 Peng Li, Wei Li, Zhengyan He, Xuguang Wang, Ying Cao, Jie zhou, Wei Xu

While question answering (QA) with neural network, i. e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system.

Answer Generation Question Answering

Semi-Supervised Learning for Neural Machine Translation

no code implementations ACL 2016 Yong Cheng, Wei Xu, Zhongjun He, wei he, Hua Wu, Maosong Sun, Yang Liu

While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation.

Machine Translation NMT +1

Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation

1 code implementation TACL 2016 Jie Zhou, Ying Cao, Xuguang Wang, Peng Li, Wei Xu

On the WMT'14 English-to-French task, we achieve BLEU=37. 7 with a single attention model, which outperforms the corresponding single shallow model by 6. 2 BLEU points.

Machine Translation NMT +1

CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases

no code implementations ACL 2016 Zihang Dai, Lei LI, Wei Xu

We propose CFO, a Conditional Focused neural-network-based approach to answering factoid questions with knowledge bases.

Question Answering

CNN-RNN: A Unified Framework for Multi-label Image Classification

1 code implementation CVPR 2016 Jiang Wang, Yi Yang, Junhua Mao, Zhiheng Huang, Chang Huang, Wei Xu

While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image.

Classification General Classification +2

A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization

no code implementations13 Apr 2016 Shun Zheng, Jialei Wang, Fen Xia, Wei Xu, Tong Zhang

In modern large-scale machine learning applications, the training data are often partitioned and stored on multiple machines.

Optimizing Statistical Machine Translation for Text Simplification

1 code implementation TACL 2016 Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, Chris Callison-Burch

Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus.

Machine Translation Sentence +2

Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks

no code implementations ICCV 2015 Chunshui Cao, Xian-Ming Liu, Yi Yang, Yinan Yu, Jiang Wang, Zilei Wang, Yongzhen Huang, Liang Wang, Chang Huang, Wei Xu, Deva Ramanan, Thomas S. Huang

While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to remember that the human visual contex contains generally more feedback connections than foward connections.

ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering

no code implementations18 Nov 2015 Kan Chen, Jiang Wang, Liang-Chieh Chen, Haoyuan Gao, Wei Xu, Ram Nevatia

ABC-CNN determines an attention map for an image-question pair by convolving the image feature map with configurable convolutional kernels derived from the question's semantics.

Question Answering Visual Question Answering

Attention to Scale: Scale-aware Semantic Image Segmentation

no code implementations CVPR 2016 Liang-Chieh Chen, Yi Yang, Jiang Wang, Wei Xu, Alan L. Yuille

We adapt a state-of-the-art semantic image segmentation model, which we jointly train with multi-scale input images and the attention model.

Image Segmentation Segmentation +1

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