Search Results for author: Yulong Wang

Found 35 papers, 11 papers with code

Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities

1 code implementation10 Jul 2024 Tianjie Ju, Yiting Wang, Xinbei Ma, Pengzhou Cheng, Haodong Zhao, Yulong Wang, Lifeng Liu, Jian Xie, Zhuosheng Zhang, Gongshen Liu

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation.

counterfactual Fact Checking +2

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

1 code implementation28 Mar 2024 Ang Lv, Yuhan Chen, Kaiyi Zhang, Yulong Wang, Lifeng Liu, Ji-Rong Wen, Jian Xie, Rui Yan

In this paper, we delve into several mechanisms employed by Transformer-based language models (LLMs) for factual recall tasks.

Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes

1 code implementation CVPR 2024 Yujie Lu, Long Wan, Nayu Ding, Yulong Wang, Shuhan Shen, Shen Cai, Lin Gao

However, common distance field based implicit representations, specifically signed distance field (SDF) for watertight shapes or unsigned distance field (UDF) for arbitrary shapes, routinely suffer from degradation of reconstruction accuracy when converting to explicit surface points and meshes.

High-Dimensional Tail Index Regression: with An Application to Text Analyses of Viral Posts in Social Media

no code implementations2 Mar 2024 Yuya Sasaki, Jing Tao, Yulong Wang

To conduct inference, we propose to debias the regularized estimate, and establish the asymptotic normality of the debiased estimator.

Inference in Auctions with Many Bidders Using Transaction Prices

no code implementations16 Nov 2023 Federico A. Bugni, Yulong Wang

Given the abundance of bidders in each auction, we propose an asymptotic framework in which the number of bidders diverges while the number of auctions remains fixed.

SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction

1 code implementation CVPR 2024 Conghao Wong, Beihao Xia, Ziqian Zou, Yulong Wang, Xinge You

Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes has become more and more significant in many intelligent systems and applications.

Diversity Pedestrian Trajectory Prediction +1

On the Inconsistency of Cluster-Robust Inference and How Subsampling Can Fix It

no code implementations20 Aug 2023 Harold D. Chiang, Yuya Sasaki, Yulong Wang

Conventional methods of cluster-robust inference are inconsistent in the presence of unignorably large clusters.


New Adversarial Image Detection Based on Sentiment Analysis

1 code implementation3 May 2023 Yulong Wang, Tianxiang Li, Shenghong Li, Xin Yuan, Wei Ni

Deep Neural Networks (DNNs) are vulnerable to adversarial examples, while adversarial attack models, e. g., DeepFool, are on the rise and outrunning adversarial example detection techniques.

Adversarial Attack Sentiment Analysis

Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey

no code implementations11 Mar 2023 Yulong Wang, Tong Sun, Shenghong Li, Xin Yuan, Wei Ni, Ekram Hossain, H. Vincent Poor

This survey provides a comprehensive overview of the recent advancements in the field of adversarial attack and defense techniques, with a focus on deep neural network-based classification models.

Adversarial Attack Adversarial Defense

Extreme Changes in Changes

no code implementations27 Nov 2022 Yuya Sasaki, Yulong Wang

This paper proposes a new CIC estimator to accurately estimate treatment effects at extreme quantiles.

Non-Robustness of the Cluster-Robust Inference: with a Proposal of a New Robust Method

no code implementations31 Oct 2022 Yuya Sasaki, Yulong Wang

In light of these negative results about the existing CR methods, we propose a weighted CR (WCR) method as a simple fix.

Double Graphs Regularized Multi-view Subspace Clustering

no code implementations30 Sep 2022 Longlong Chen, Yulong Wang, Youheng Liu, Yutao Hu, Libin Wang

In this paper, we propose a novel Double Graphs Regularized Multi-view Subspace Clustering (DGRMSC) method, which aims to harness both global and local structural information of multi-view data in a unified framework.

Clustering Multi-view Subspace Clustering

Global Weighted Tensor Nuclear Norm for Tensor Robust Principal Component Analysis

no code implementations28 Sep 2022 Libin Wang, Yulong Wang, Shiyuan Wang, Youheng Liu, Yutao Hu, Longlong Chen, Hong Chen

Tensor Robust Principal Component Analysis (TRPCA), which aims to recover a low-rank tensor corrupted by sparse noise, has attracted much attention in many real applications.

Dispersed Pixel Perturbation-based Imperceptible Backdoor Trigger for Image Classifier Models

no code implementations19 Aug 2022 Yulong Wang, Minghui Zhao, Shenghong Li, Xin Yuan, Wei Ni

In this paper, we propose a new backdoor trigger, which is easy to generate, imperceptible, and highly effective.

Capital and Labor Income Pareto Exponents in the United States, 1916-2019

no code implementations9 Jun 2022 Ji Hyung Lee, Yuya Sasaki, Alexis Akira Toda, Yulong Wang

Accurately estimating income Pareto exponents is challenging due to limitations in data availability and the applicability of statistical methods.

Tuning Parameter-Free Nonparametric Density Estimation from Tabulated Summary Data

no code implementations12 Apr 2022 Ji Hyung Lee, Yuya Sasaki, Alexis Akira Toda, Yulong Wang

Administrative data are often easier to access as tabulated summaries than in the original format due to confidentiality concerns.

Density Estimation

Non-Existent Moments of Earnings Growth

no code implementations15 Mar 2022 Silvia Sarpietro, Yuya Sasaki, Yulong Wang

Our empirical analysis reveals that population kurtosis, skewness, and variance often do not exist for the conditional distribution of earnings growth.

Error-based Knockoffs Inference for Controlled Feature Selection

no code implementations9 Mar 2022 Xuebin Zhao, Hong Chen, Yingjie Wang, Weifu Li, Tieliang Gong, Yulong Wang, Feng Zheng

Recently, the scheme of model-X knockoffs was proposed as a promising solution to address controlled feature selection under high-dimensional finite-sample settings.

Feature Importance feature selection

Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters

1 code implementation10 Nov 2021 Xiangru Lian, Binhang Yuan, XueFeng Zhu, Yulong Wang, Yongjun He, Honghuan Wu, Lei Sun, Haodong Lyu, Chengjun Liu, Xing Dong, Yiqiao Liao, Mingnan Luo, Congfei Zhang, Jingru Xie, Haonan Li, Lei Chen, Renjie Huang, Jianying Lin, Chengchun Shu, Xuezhong Qiu, Zhishan Liu, Dongying Kong, Lei Yuan, Hai Yu, Sen yang, Ce Zhang, Ji Liu

Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.

Recommendation Systems

Three-dimensional Cooperative Localization of Commercial-Off-The-Shelf Sensors

no code implementations3 Nov 2021 Yulong Wang, Shenghong Li, Wei Ni, David Abbott, Mark Johnson, Guangyu Pei, Mark Hedley

We propose an efficient approach to solve the corresponding permutation combinatorial optimization problem, which integrates continuous space cooperative localization and permutation space likelihood ascent search.

Combinatorial Optimization

Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese

1 code implementation13 Oct 2021 Zhuosheng Zhang, Hanqing Zhang, Keming Chen, Yuhang Guo, Jingyun Hua, Yulong Wang, Ming Zhou

Although pre-trained models (PLMs) have achieved remarkable improvements in a wide range of NLP tasks, they are expensive in terms of time and resources.

Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective

no code implementations18 Jun 2021 Lina Wang, Xingshu Chen, Yulong Wang, Yawei Yue, Yi Zhu, Xuemei Zeng, Wei Wang

Previous works study the adversarial robustness of image classifiers on image level and use all the pixel information in an image indiscriminately, lacking of exploration of regions with different semantic meanings in the pixel space of an image.

Adversarial Robustness

Fixed-k Tail Regression: New Evidence on Tax and Wealth Inequality from Forbes 400

no code implementations20 May 2021 Ji Hyung Lee, Yuya Sasaki, Alexis Akira Toda, Yulong Wang

We develop a novel fixed-k tail regression method that accommodates the unique feature in the Forbes 400 data that observations are truncated from below at the 400th largest order statistic.

regression Time Series Analysis

Question-Driven Span Labeling Model for Aspect–Opinion Pair Extraction

no code implementations AAAI 2021 Lei Gao, Yulong Wang, Tongcun Liu, Jingyu Wang, Lei Zhang, Jianxin Liao

Specifically, we divide the AOPE task into aspect term extraction (ATE) and aspect-specified opinion extraction (ASOE) subtasks; we first extract all the candidate aspect terms and then the corresponding opinion words given the aspect term.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

Semantic Segmentation by Improved Generative Adversarial Networks

no code implementations20 Apr 2021 ZengShun Zhaoa, Yulong Wang, Ke Liu, Haoran Yang, Qian Sun, Heng Qiao

Besides, the adversarial loss aggressively encourages the output image to be close to the distribution of the ground truth.

Segmentation Semantic Segmentation

Data-Free Adversarial Perturbations for Practical Black-Box Attack

no code implementations3 Mar 2020 ZhaoXin Huan, Yulong Wang, Xiaolu Zhang, Lin Shang, Chilin Fu, Jun Zhou

Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted for one model can fool another model.

6D Object Pose Regression via Supervised Learning on Point Clouds

1 code implementation24 Jan 2020 Ge Gao, Mikko Lauri, Yulong Wang, Xiaolin Hu, Jianwei Zhang, Simone Frintrop

We use depth information represented by point clouds as the input to both deep networks and geometry-based pose refinement and use separate networks for rotation and translation regression.

Object regression +1

Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork

no code implementations7 Oct 2019 Yulong Wang, Xiaolin Hu, Hang Su

We also apply extracted subnetworks in visual explanation and adversarial example detection tasks by merely replacing the original full model with class-specific subnetworks.


Pruning from Scratch

1 code implementation27 Sep 2019 Yulong Wang, Xiaolu Zhang, Lingxi Xie, Jun Zhou, Hang Su, Bo Zhang, Xiaolin Hu

Network pruning is an important research field aiming at reducing computational costs of neural networks.

Network Pruning

Threshold Regression with Nonparametric Sample Splitting

no code implementations30 May 2019 Yoonseok Lee, Yulong Wang

This paper develops a threshold regression model where an unknown relationship between two variables nonparametrically determines the threshold.


Interpret Neural Networks by Identifying Critical Data Routing Paths

no code implementations CVPR 2018 Yulong Wang, Hang Su, Bo Zhang, Xiaolin Hu

Interpretability of a deep neural network aims to explain the rationale behind its decisions and enable the users to understand the intelligent agents, which has become an important issue due to its importance in practical applications.

A Hierarchical Recurrent Neural Network for Symbolic Melody Generation

2 code implementations14 Dec 2017 Jian Wu, Changran Hu, Yulong Wang, Xiaolin Hu, Jun Zhu

In this paper, we present a hierarchical recurrent neural network for melody generation, which consists of three Long-Short-Term-Memory (LSTM) subnetworks working in a coarse-to-fine manner along time.

Sound Multimedia

Modal Regression based Atomic Representation for Robust Face Recognition

no code implementations5 Nov 2017 Yulong Wang, Yuan Yan Tang, Luoqing Li, Hong Chen

In this paper, we propose a modal regression based atomic representation and classification (MRARC) framework to alleviate such limitation.

Face Recognition General Classification +2

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