Yu Wang

Improving the Speed of Response of Learning Algorithms Using Multiple Models

2015 · arXiv (Cornell University)

This is the first of a series of papers that the authors propose to write on the subject of improving the speed of response of learning systems using multiple models. During the past two decades, …

Analysis of Web Access Sequence Based on the Improved Prefix Span Algorithm

2015 · Advances in computer science research

PrefixSpan is an important algorithm for sequential pattern mining algorithm, but it's projected database cost more redundant memory and scan-time, so this paper present an improved PrefixSpan algorithm(IPS) which is based on PrefixSpan. IPS decreases …

An Improved Artificial Bee Colony Algorithm for Cloud Computing Service Composition

2015

The rapid increase of using cloud computing encourages service vendors to supply services with different features and provide them in a service pool. Service composition (SC) problem in cloud computing environment becomes a key issue …

Personalized recommendation method based on user behavior analysis

2017

The characteristics of user's behavior in the real scene are analyzed, and a personalized recommendation method based on user behavior analysis is put forward. In the electronic commerce user behavior can be divided into clicking, …

Unified Language Model Pre-training for Natural Language Understanding and Generation

2019 · arXiv (Cornell University)

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, …

Learning a Static Bug Finder from Data

2019 · arXiv (Cornell University)

We present an alternative approach to creating static bug finders. Instead of relying on human expertise, we utilize deep neural networks to train static analyzers directly from data. In particular, we frame the problem of …

Pricing the woman card: Gender politics between hillary clinton and donald trump

2016

In this paper, we introduce computer vision to the study of gender politics and present a data-driven method to measure the impact of the `woman card' exchange between Hillary Clinton and Donald Trump. Building from …

Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift

2019 · arXiv (Cornell University)

A novel variational inference based resampling framework is proposed to evaluate the robustness and generalization capability of deep learning models with respect to distribution shift. We use Auto Encoding Variational Bayes to find a latent …

An Identity-based Aggregate Signature Scheme for Wireless Sensor Network Environmental Monitoring

2019

Aggregation signature technology can save transmission bandwidth and computational cost while providing message authentication for multiple users. It is suitable for message aggregation and batch signature verification in wireless sensor network environment monitoring. Based on …

Similarity detection of English text and teaching evaluation based on improved TCUSS clustering algorithm

2020 · Journal of Intelligent & Fuzzy Systems

The semantic similarity calculation task of English text has important influence on other fields of natural language processing and has high research value and application prospect. At present, research on the similarity calculation of short …

A computational prediction method based on modified U-Net for cell distribution in tumor microenvironment

2021

The tumor microenvironment (TME) is the internal environment in which tumors develop and consist of tumor cells, various immune cells, and interstitial cells. Understanding different cell distribution in TME can help predict clinical response of …

Deep Learning-Based Service Discovery for Business Process Re-Engineering in the Era of Big Data

2020 · International Journal of Big Data Intelligence and Applications

In recent years, business process re-engineering has played an important role in the development of large-scale web-based applications. To re-engineer business processes, business services are developed and coordinated by reusing a set of open APIs …

Adversarial Response Generation Against Topic Relevance

2021 · Journal of Physics Conference Series

Abstract In recent years, generative adversarial networks have performed well in the field of dialogue generation to improve the information diversity of dialogue responses. Often overlooked, however, is that the query and response are not …

Learning Robust Recommenders through Cross-Model Agreement

2022 · Proceedings of the ACM Web Conference 2022

Learning from implicit feedback is one of the most common cases in the application of recommender systems. Generally speaking, interacted examples are considered as positive while negative examples are sampled from uninteracted ones. However, noisy …

Predicting Solar Flares using CNN and LSTM on Two Solar Cycles of Active Region Data

2021

We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm …

Ultra Lite Convolutional Neural Network for Fast Automatic Modulation Classification in Low-Resource Scenarios

2022 · arXiv (Cornell University)

Automatic modulation classification (AMC) is a key technique for designing non-cooperative communication systems, and deep learning (DL) is applied effectively to AMC for improving classification accuracy. However, most of the DL-based AMC methods have a …

Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization

2022 · arXiv (Cornell University)

Outlier detection tasks have been playing a critical role in AI safety. There has been a great challenge to deal with this task. Observations show that deep neural network classifiers usually tend to incorrectly classify …

Controlling Bias Exposure for Fair Interpretable Predictions

2022 · arXiv (Cornell University)

Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive information is semantically entangled with the task information …

Disentangled Retrieval and Reasoning for Implicit Question Answering

2022 · IEEE Transactions on Neural Networks and Learning Systems

To date, most of the existing open-domain question answering (QA) methods focus on explicit questions where the reasoning steps are mentioned explicitly in the question. In this article, we study implicit QA where the reasoning …

Neural Coreference Resolution based on Reinforcement Learning

2022 · arXiv (Cornell University)

The target of a coreference resolution system is to cluster all mentions that refer to the same entity in a given context. All coreference resolution systems need to solve two subtasks; one task is to …

Online Semi-supervised Learning with Mix-Typed Streaming Features

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Online learning with feature spaces that are not fixed but can vary over time renders a seemingly flexible learning paradigm thus has drawn much attention. Unfortunately, two restrictions prohibit a ubiquitous application of this learning …

Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory

2023 · arXiv (Cornell University)

Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical aspect of risk awareness involves modeling highly rare risk events …

Exploring Diverse Representations for Open Set Recognition

2024 · arXiv (Cornell University)

Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR, but recent studies …

Few-Shot Domain Adaption-Based Specific Emitter Identification Under Varying Modulation

2023

Specific emitter identification (SEI) is an effective Internet of things (IoT) data flow protection technique of identifying individual emitters via unique characteristics of different emitters. However, deep learning-based methods are difficult to deal with the …

Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions, yet their application within the medical field remains insufficiently explored. Previous works mainly focus on the performance of medical knowledge with examinations, which is …

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models

2024 · arXiv (Cornell University)

In recent years, there has been significant progress in the development of text-to-image generative models. Evaluating the quality of the generative models is one essential step in the development process. Unfortunately, the evaluation process could …

SQL injection attack sample generation based on IE-GAN

2023

The relentless advancement of Generative Adversarial Network (GAN) technology has stimulated research interest in exploiting its unique properties within the realm of network security. In conjunction with the maturity and growth of artificial intelligence, employing …

Self-Updatable Large Language Models by Integrating Context into Model Parameters

2024 · arXiv (Cornell University)

Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with surrounding objects, remains a substantial challenge. Two critical factors in assimilating these experiences are (1) …

Entity-level cross-modal fusion for multimodal chinese agricultural diseases and pests named entity recognition

2025 · Smart Agricultural Technology

Named Entity Recognition 1 (NER), as one of the popular directions in natural language processing, plays a critical role in fields such as information extraction and agricultural knowledge graph construction. However, traditional single modal methods …

A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation

2025 · arXiv (Cornell University)

In recent years, non-intrusive load monitoring (NILM) technology has attracted much attention in the related research field by virtue of its unique advantage of utilizing single meter data to achieve accurate decomposition of device-level energy …

CS3-Bench: Evaluating and Enhancing Speech-to-Speech LLMS for Mandarin-English Code-Switching

2026

The advancement of multimodal large language models has accelerated the development of speech-to-speech interaction systems. While natural monolingual interaction has been achieved, we find existing models exhibit deficiencies in language alignment. In our proposed Code-Switching …

Statistical learning of stochastic complex systems via the Yau-Yau nonlinear filter

2026 · The Innovation

Complex systems are characterized by nonlinearity, uncertainty, and noise interference, making it challenging to unravel their internal operation mechanisms. Here, we overcome this issue by implementing the Yau-Yau nonlinear filter theory to reconstruct stochastic networks …

Adversarial Training for Large Neural Language Models

2020 · arXiv (Cornell University)

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training large neural language models …