Xin Wang

An autoregressive recurrent mixture density network for parametric speech synthesis

2017

Neural-network-based generative models, such as mixture density networks, are potential solutions for speech synthesis. In this paper we follow this path and propose a recurrent mixture density network that incorporates a trainable autoregressive model. An …

Intelligent RDD Management for High Performance In-Memory Computing in Spark

2017

Spark is a pervasively used in-memory computing framework in the era of big data, and can greatly accelerate the computation speed by wrapping the accessed data as resilient distribution datasets (RDDs) and storing these datasets …

Human Resource Information Management Model based on Blockchain Technology

2017

The authenticity of human resource information has become an important factor that affects the cost and efficiency of human resource management. With the rapid development of mobile devices and Internet technology, various human resource risks …

$Q|SI\rangle$: A Quantum Programming Environment

2017 · arXiv (Cornell University)

This paper describes a quantum programming environment, named $Q|SI\rangle$. It is a platform embedded in the .Net language that supports quantum programming using a quantum extension of the $\mathbf{while}$-language. The framework of the platform includes …

The Influence of Task-Based Language Teaching Approach on Foreign Language Anxiety and Achievements among Vocational College Students

2018 · DEStech Transactions on Social Science Education and Human Science

This paper takes non-English majors of vocational college as research individuals, investigating and analyzing their foreign language anxiety and English learning achievement, then adopting task-based teaching approach and 3P (presentation-practice-production) teaching method in the contrast. …

Automatic Diagnosis Technology of Lightning Fault in Transmission Line

2018

Lightning fault is the main fault of transmission line. Accurate and effective diagnosis of lightning fault can effectively improve the reliability level of transmission line. At present, the determination of lightning strike fault and the …

Anonymous Identity-Based Encryption with Identity Recovery

2018 · arXiv (Cornell University)

Anonymous Identity-Based Encryption can protect privacy of the receiver. However, there are some situations that we need to recover the identity of the receiver, for example a dispute occurs or the privacy mechanism is abused. …

Second-Order Fault Tolerant Extended Kalman Filter for Discrete Time Nonlinear Systems

2019 · IEEE Transactions on Automatic Control

As missing sensor data may severely degrade the overall system performance and stability, reliable state estimation is of great importance in modern data-intensive control, computing, and power systems applications. Aiming at providing a more robust …

Compositional Coding for Collaborative Filtering

2019

Efficiency is crucial to the online recommender systems, especially for the ones which needs to deal with tens of millions of users and items. Because representing users and items as binary vectors for Collaborative Filtering …

Resource theory of asymmetric distinguishability

2019 · Physical Review Research

This paper puts forward the proposition that distinguishability is a resource that can be quantified and interconverted by means of basic units. The authors also show that relative entropy and its variants find fundamental operational …

Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation

2019 · arXiv (Cornell University)

The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo …

Resource theory of entanglement for bipartite quantum channels

2019 · arXiv (Cornell University)

The traditional perspective in quantum resource theories concerns how to use free operations to convert one resourceful quantum state to another one. For example, a fundamental and well known question in entanglement theory is to …

Initial investigation of an encoder-decoder end-to-end TTS framework using marginalization of monotonic hard latent alignments

2019 · arXiv (Cornell University)

End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, …

Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings

2019 · arXiv (Cornell University)

While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate multi-speaker modeling for …

The Research on Bridge Engineering Risk Management and Assessment Model Based on BP Neural Network

2020 · IOP Conference Series Earth and Environmental Science

Abstract Bridge engineering risk research is an important part of bridge engineering management. This paper establishes the risk indicators system of bridge project, and then introduces BP neural network theory into bridge risk evaluation. By …

Disentangled Self-Supervision in Sequential Recommenders

2020

To learn a sequential recommender, the existing methods typically adopt the sequence-to-item (seq2item) training strategy, which supervises a sequence model with a user's next behavior as the label and the user's past behaviors as the …

Towards application performance fairness on clouds

2020

In cloud computing, resource allocation is the key building block. Existing resource allocation strategies are designed for multi-tenant cases and the majority of them target resource fairness and utilization. We consider the problem of resource …

Determination of Basic Probability Assignment Based on Probability Distribution

2020

In the application of Dempster-Shafer (D-S) evidence theory, the determination of basic probability assignment (BPA) is a key step. How to determine BPA is an open issue. To solve this problem, a new method to …

Fast Local Attack: Generating Local Adversarial Examples for Object Detectors

2020 · arXiv (Cornell University)

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object detectors, but they …

Physical Implementability of Quantum Maps and Its Application in Error Mitigation

2020 · arXiv (Cornell University)

Completely positive and trace-preserving maps characterize physically implementable quantum operations. On the other hand, general quantum maps, such as positive but not completely positive maps, which can not be physically implemented, are fundamental ingredients in …

Identifying Mis-Configured Author Profiles on Google Scholar Using Deep Learning

2021 · Applied Sciences

Google Scholar has been a widely used platform for academic performance evaluation and citation analysis. The issue about the mis-configuration of author profiles may seriously damage the reliability of the data, and thus affect the …

Distilling Holistic Knowledge with Graph Neural Networks

2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network. Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the …

Efficiently Solve the Max-cut Problem via a Quantum Qubit Rotation Algorithm

2021 · arXiv (Cornell University)

Optimizing parameterized quantum circuits promises efficient use of near-term quantum computers to achieve the potential quantum advantage. However, there is a notorious tradeoff between the expressibility and trainability of the parameter ansatz. We find that …

Efficient Learning to Learn a Robust CTR Model for Web-scale Online Sponsored Search Advertising

2021

Click-through rate (CTR) prediction is crucial for online sponsored search advertising. Several successful CTR models have been adopted in the industry, including the regularized logistic regression (LR). Nonetheless, the learning process suffers from two limitations: …

Local Epochs Inefficiency Caused by Device Heterogeneity in Federated Learning

2022 · Wireless Communications and Mobile Computing

Federated learning is a new framework of machine learning, it trains models locally on multiple clients and then uploads local models to the server for model aggregation iteratively until the model converges. In most cases, …

FedVLN: Privacy-preserving Federated Vision-and-Language Navigation

2022 · arXiv (Cornell University)

Data privacy is a central problem for embodied agents that can perceive the environment, communicate with humans, and act in the real world. While helping humans complete tasks, the agent may observe and process sensitive …

Analysis and Design of Power System Transformer Standard Based on Knowledge Graph

2022 · ICST Transactions on Scalable Information Systems

The transformer can convert one kind of electric energy such as AC current and AC voltage into another kind of electric energy with the same frequency. Knowledge graph (KG) can describe various entities and concepts …

Blockchain Mining With Multiple Selfish Miners

2023 · IEEE Transactions on Information Forensics and Security

This paper studies a fundamental problem regarding the security of blockchain PoW consensus on how the existence of multiple misbehaving miners influences the profitability of selfish mining. Each selfish miner maintains a private chain and …

Outlier Robust Adversarial Training

2023 · arXiv (Cornell University)

Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning methods and the recent …

Quantum hypothesis testing via robust quantum control

2023 · arXiv (Cornell University)

Quantum hypothesis testing plays a pivotal role in quantum technologies, making decisions or drawing conclusions about quantum systems based on observed data. Recently, quantum control techniques have been successfully applied to quantum hypothesis testing, enabling …

Causal-aware Graph Neural Architecture Search under Distribution Shifts

2024 · arXiv (Cornell University)

Graph NAS has emerged as a promising approach for autonomously designing GNN architectures by leveraging the correlations between graphs and architectures. Existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph …

Large Language Model Enhanced Knowledge Representation Learning: A Survey

2024 · arXiv (Cornell University)

Knowledge Representation Learning (KRL) is crucial for enabling applications of symbolic knowledge from Knowledge Graphs (KGs) to downstream tasks by projecting knowledge facts into vector spaces. Despite their effectiveness in modeling KG structural information, KRL …

Improving text classification via computing category correlation matrix from text graph

2024 · Computer Speech & Language

In text classification task , models have shown remarkable accuracy across various datasets. However, confusion often arises when certain categories within the dataset are too similar, causing misclassification of certain samples. This paper proposes an …

Scaling Laws for Post Training Quantized Large Language Models

2024 · arXiv (Cornell University)

Generalization abilities of well-trained large language models (LLMs) are known to scale predictably as a function of model size. In contrast to the existence of practical scaling laws governing pre-training, the quality of LLMs after …

NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls

2024 · arXiv (Cornell University)

The resurgence of autonomous agents built using large language models (LLMs) to solve complex real-world tasks has brought increased focus on LLMs' fundamental ability of tool or function calling. At the core of these agents, …

Curriculum Learning for Multimedia in the Era of Large Language Models

2024

This tutorial focuses on curriculum learning (CL), an important topic in machine learning, which gains an increasing amount of attention in the research community. CL is a learning paradigm that enables machines to learn from …

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning

2024 · arXiv (Cornell University)

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a …

Semantic Communication System for Standard Knowledge in Power Iot Networks

2025 · Computational Intelligence

ABSTRACT The growing complexity of power Internet of Things (IoT) networks necessitates efficient and reliable communication capable of handling the continuous stream of data generated by distributed sensors, smart meters, and control systems. To handle …

Aligning Large Multimodal Model with Sequential Recommendation via Content-Behavior Guidance

2025

Large language models (LLMs) have significantly influenced advancements in sequential recommendation. Nevertheless, the integration and alignment of LLMs with sequence recommenders is often underexploited in current research. Existing LLM-based sequential recommenders mostly rely on textual …

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS

2025 · arXiv (Cornell University)

Test-time scaling has emerged as a promising paradigm in language modeling, leveraging additional computational resources at inference time to enhance model performance. In this work, we introduce R2-LLMs, a novel and versatile hierarchical retrieval-augmented reasoning …

BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks

2026

Rui Miao, Yixin Liu, Yili Wang, Xu Shen, Yue Tan, Yiwei Dai, Shirui Pan, Xin Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Data Skeleton Learning: Scalable Active Clustering with Sparse Graph Structures

2025 · arXiv (Cornell University)

In this work, we focus on the efficiency and scalability of pairwise constraint-based active clustering, crucial for processing large-scale data in applications such as data mining, knowledge annotation, and AI model pre-training. Our goals are …

No-Go Theorems for Universal Quantum State Purification via Classically Simulable Operations

2026 · Physical Review Letters

Quantum state purification, a process that aims to recover a state closer to a system's principal eigenstate from multiple copies of an unknown noisy quantum state, is crucial for restoring noisy states to a more …

Targeted Adversarial Camouflage Texture for Fooling Object Detectors via Native Supervision Redirection

2026 · Entropy

Adversarial camouflage has attracted growing research attention owing to its ability to execute multi-view, persistent attacks in real physical environments, outperforming conventional single-view adversarial patches. However, most existing methods are confined to non-targeted attacks, which …

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation

2021 · arXiv (Cornell University)

Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence. Recently, many pre-trained language models for source code (e.g., …