Jun Wang

Fletcher-Reeves learning approach for high order MQAM signal modulation recognition

2016

A new method of Modulation Recognition of communication signals is proposed based on Clustering Validity Indices. These indices provide a good basis for key feature extraction. To distinguish different modulation schemes, a Fuzzy C-mean (FCM) …

Detecting Adversarial Examples via Key-based Network

2018 · arXiv (Cornell University)

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to the input images …

Differentially Private Neighborhood-based Recommender Systems

2017 · arXiv (Cornell University)

Privacy issues of recommender systems have become a hot topic for the society as such systems are appearing in every corner of our life. In contrast to the fact that many secure multi-party computation protocols …

EMLR for multiple radars on a mobile platform

2019 · The Journal of Engineering

Aiming at the problem of radar sensor registration on a mobile platform, this study uses multiple radars to estimate the biases of the radar under the earth‐centred earth‐fixed coordinate system, which provides more accurate information …

Modulation classification based on denoising autoencoder and convolutional neural network with GNU radio

2019 · The Journal of Engineering

In this article, a machine learning method to classify signal with Gaussian noise based on denoising auto encoder (DAE) and convolutional neural network (CNN) is proposed. We combine denoising autoencoder's denoising ability with CNN's feature …

Partial Multi-label Learning with Label and Feature Collaboration

2020 · arXiv (Cornell University)

Partial multi-label learning (PML) models the scenario where each training instance is annotated with a set of candidate labels, and only some of the labels are relevant. The PML problem is practical in real-world scenarios, …

JIT2R: A Joint Framework for Item Tagging and Tag-based Recommendation

2020

Predicting tags for a given item and leveraging tags to assist item recommendation are two popular research topics in the field of recommender system. Previous studies mostly focus only one of them to make contributions. …

Discrete Dynamic Bayesian Network Threat Assessment Method Based on Cloud Parameter Learning

2019 · 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP)

Aiming at the problem that the data is easily divided inaccurately at the conceptual junction after the discretization of the target continuous threat variable, a Discretization Dynamic Bayesian Network (DDBN)parameter learning algorithm based on cloud …

A Shilling Attack Model Based on TextCNN

2020 · 2020 IEEE 3rd International Conference on Automation, Electronics and Electrical Engineering (AUTEEE)

With the development of the Internet, the amount of information on the Internet is increasing rapidly, which makes it difficult for people to select the information they really want. A recommendation system is an effective …

PAC Learnability of Approximate Nash Equilibrium in Bimatrix Games

2021 · arXiv (Cornell University)

Computing Nash equilibrium in bimatrix games is PPAD-hard, and many works have focused on the approximate solutions. When games are generated from a fixed unknown distribution, learning a Nash predictor via data-driven approaches can be …

Viscos Flows: Variational Schur Conditional Sampling With Normalizing Flows

2021 · arXiv (Cornell University)

We present a method for conditional sampling for pre-trained normalizing flows when only part of an observation is available. We derive a lower bound to the conditioning variable log-probability using Schur complement properties in the …

Settling the Communication Complexity for Distributed Offline Reinforcement Learning

2022 · arXiv (Cornell University)

We study a novel setting in offline reinforcement learning (RL) where a number of distributed machines jointly cooperate to solve the problem but only one single round of communication is allowed and there is a …

Graph neural network for merger and acquisition prediction

2021

This paper investigates the application of graph neural networks (GNN) in Mergers and Acquisitions (M&A) prediction, which aims to quantify the relationship between companies, their founders, and investors. M&A is a critical management strategy to …

Trinet: Stabilizing Self-Supervised Learning From Complete or Slow Collapse

2023

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the pretraining. TriNet learns the SSL latent …

Conformal Temporal Logic Planning using Large Language Models

2023 · arXiv (Cornell University)

This paper addresses planning problems for mobile robots. We consider missions that require accomplishing multiple high-level sub-tasks, expressed in natural language (NL), in a temporal and logical order. To formally define the mission, we treat …

Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning

2023 · arXiv (Cornell University)

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of …

On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective

2023 · CAAI Artificial Intelligence Research

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively …

Logic Synthesis with Generative Deep Neural Networks

2024 · arXiv (Cornell University)

While deep learning has achieved significant success in various domains, its application to logic circuit design has been limited due to complex constraints and strict feasibility requirement. However, a recent generative deep neural model, "Circuit …

Stabilization Control for a Kind of Finite Probabilistic Transition System Subjects to Communication Faults

2024

For networked control systems (NCS) with data packet dropouts and bounded time delay, stabilization control was studied in this paper: Data flow transmission faults such as data packet dropout and time delay are integrated into …

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

2024 · arXiv (Cornell University)

In this technical report, we introduce OpenR, an open-source framework designed to integrate key components for enhancing the reasoning capabilities of large language models (LLMs). OpenR unifies data acquisition, reinforcement learning training (both online and …

On Almost Surely Safe Alignment of Large Language Models at Inference-Time

2025 · arXiv (Cornell University)

We introduce a novel inference-time alignment approach for LLMs that aims to generate safe responses almost surely, i.e., with probability approaching one. Our approach models the generation of safe responses as a constrained Markov Decision …

Research and Application of Intelligent Governance Technology for Non-Motor Vehicle Violations

2025 · Procedia Computer Science

With the rapid development of the economy and society, the number of motor vehicles and non-motorized vehicles has increased significantly, leading to a continuous rise in traffic accidents. Particularly, illegal behaviors involving non-motorized vehicles not …

Interaction Privacy Vulnerability in Federated Recommendation and Lossless Countermeasure

2025 · ACM Transactions on Information Systems

Federated Recommendation (FedRec) systems are recognized as privacy-preserving solutions for collaboratively training recommender models without sharing users’ private data. However, recent studies have revealed that FedRec systems are vulnerable to interaction-level membership inference attacks. In …

Carbon Emission Anomaly Monitoring Method Based on Multidimensional Clustering and Intelligent Analysis

2025

In order to achieve the accurate monitoring and anomaly identification of carbon emissions in complex multiscenarios, this paper proposes a carbon emission anomaly monitoring method based on multi-dimensional clustering and intelligent analysis. Firstly, a carbon-electric …

Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems

2025 · arXiv (Cornell University)

Recent years have witnessed extensive exploration of Large Language Models (LLMs) on the field of Recommender Systems (RS). There are currently two commonly used strategies to enable LLMs to have recommendation capabilities: 1) The "Guidance-Only" …

Product-Based Neural Networks for User Response Prediction

2016

Predicting user responses, such as clicks and conversions, is of great importance and has found its usage inmany Web applications including recommender systems, websearch and online advertising. The data in those applicationsis mostly categorical and …

Texygen: A Benchmarking Platform for Text Generation Models

2018 · arXiv (Cornell University)

We introduce Texygen, a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the …

Explanation Mining

2018

The widescale use of machine learning algorithms to drive decision-making has highlighted the critical importance of ensuring the interpretability of such models in order to engender trust in their output. The state-of-the-art recommendation systems use …

Long Text Generation via Adversarial Training with Leaked Information

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets(GAN) that use a discriminative model to guide the …

Texygen

2018

We introduce Texygen, a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the …

PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

2021 · arXiv (Cornell University)

Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demonstrated strong performances on natural language understanding and generation with …