Hao Wang

The design of virtual maintenance system based on PHM

2016

This paper introduces the concept of PHM system and designs a virtual maintenance system based on PHM. The system architecture combined the service-oriented architecture and cloud computing. Choose free open-source alternative development environment to develop …

Actively Detecting Patterns in an Artificial Language to Learn Non-Adjacent Dependencies.

2017 · eScholarship (California Digital Library)

Many grammatical dependencies in natural language involve elements that are not adjacent, such as between thesubject and verb in ”the dog always barks”. We recently showed that non-adjacent dependencies are easily learnable withoutpauses in the …

A Rhombic Dodecahedron Topology for Human-Centric Banking Big Data

2019 · IEEE Transactions on Computational Social Systems

Banks are collecting an unprecedentedly large amount of data about their customers from difference sources, considering their cyber, physical, social activities. The focus of this paper is to study the problem of information sharing and …

Enhancing Collaborative Filtering with Generative Augmentation

2019

Collaborative filtering (CF) has become one of the most popular and widely used methods in recommender systems, but its performance degrades sharply for users with rare interaction data. Most existing hybrid CF methods try to …

The first principle of neural circuit and the general Circuit-Probability theory

2018 · arXiv (Cornell University)

A new neural circuit is proposed by considering the myelin as an inductor. This new neural circuit can explain why the lump-parameter circuit used in previous C-P theory is valid. Meanwhile, it provides a new …

Partially Shared Adversarial Learning For Semi-supervised Multi-platform User Identity Linkage

2019

With the increasing popularity and diversity of social media, users tend to join multiple social platforms to enjoy different types of services. User identity linkage, which aims to link identical identities across different social platforms, …

To Split or Not to Split: The Impact of Disparate Treatment in Classification

2020 · arXiv (Cornell University)

Disparate treatment occurs when a machine learning model yields different decisions for individuals based on a sensitive attribute (e.g., age, sex). In domains where prediction accuracy is paramount, it could potentially be acceptable to fit …

Privacy-Preserving Transactive Energy Management for IoT-Aided Smart Homes via Blockchain

2021 · IEEE Internet of Things Journal

With the booming of smart grid, the ubiquitously deployed smart meters constitutes an energy Internet of Things (IoT). This article develops a novel blockchain-based transactive energy management (TEM) system for IoT-aided smart homes. We consider …

To Split or not to Split: The Impact of Disparate Treatment in Classification

2021 · IEEE Transactions on Information Theory

Disparate treatment occurs when a machine learning model produces different decisions for individuals based on a legally protected or sensitive attribute (e.g., age, sex). In domains where prediction accuracy is paramount, it could potentially be …

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

2022 · arXiv (Cornell University)

Conventionally, Earth system (e.g., weather and climate) forecasting relies on numerical simulation with complex physical models and are hence both expensive in computation and demanding on domain expertise. With the explosive growth of the spatiotemporal …

Prediction of Hard Drive Failures for Data Center Based on LightGBM

2022

Today, industrial-scale organizations increasingly rely on data centers to store and process data. Therefore, it is of great value to protect data security and reduce the cost of data center if operators can accurately predict …

Chinese Lexical Sememe Prediction Using CilinE Knowledge

2022 · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences

Sememes are the smallest semantic units of human languages, the composition of which can represent the meaning of words. Sememes have been successfully applied to many downstream applications in natural language processing (NLP) field. Annotation …

Quantum-Inspired Solvers on Mixed-Integer Linear Programming Problem

2022 · 2022 41st Chinese Control Conference (CCC)

Mixed-integer linear programming (MILP) plays a crucial role in artificial intelligence, biochemistry, finance, cryp-tography, etc. Notwithstanding popular for decades, the researches of MILP solvers are still limited by the resource consumption caused by complexity and …

Safe Deep Reinforcement Learning Based on Sample Value Evaluation

2022

In recent years, deep reinforcement learning has combined the advantages of reinforcement learning and deep learning, and has made great progress in decision-making tasks. However, the training of deep reinforcement learning requires frequent interactions between …

Post-processing Private Synthetic Data for Improving Utility on Selected Measures

2023 · arXiv (Cornell University)

Existing private synthetic data generation algorithms are agnostic to downstream tasks. However, end users may have specific requirements that the synthetic data must satisfy. Failure to meet these requirements could significantly reduce the utility of …

A multi-source heterogeneous data-driven method for the site selection of elderly care facilities

2023 · Research Square

Abstract In the site selection of elderly care facilities era, the traditional methods of site selection for elderly care facilities are subjective, the data sources of methods are single, and the research objects of the …

Capsule Network Based on Multi-granularity Attention Model for Text Classification

2022

Text classification is a challenging task aimed at identifying categories of text. In order to improve the feature extraction capability of existing shallow text classification models and extract text information hierarchically from bottom to top, …

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

2023 · arXiv (Cornell University)

This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched …

How Far Have We Gone in Vulnerability Detection Using Large Language Models

2023 · arXiv (Cornell University)

As software becomes increasingly complex and prone to vulnerabilities, automated vulnerability detection is critically important, yet challenging. Given the significant successes of large language models (LLMs) in various tasks, there is growing anticipation of their …

A Lightweight CNN-Conformer Model for Automatic Speaker Verification

2023 · IEEE Signal Processing Letters

Recently, Conformer has achieved tremendous success in speaker verification task. It demonstrates that Transformer-based model can achieve remarkable performance in this domain, bypassing the need for intricate pre-training procedures. However, its special macaron-style feed-forward module …

Trainability maximization using estimation of distribution algorithms assisted by surrogate modelling for quantum architecture search

2024 · EPJ Quantum Technology

Abstract Quantum architecture search (QAS) involves optimizing both the quantum parametric circuit configuration but also its parameters for a variational quantum algorithm. Thus, the problem is known to be multi-level as the performance of a …

Emotional Dimension Control in Language Model-Based Text-To-Speech: Spanning a Broad Spectrum of Human Emotions

2026

Emotional text-to-speech (TTS) systems struggle to capture the full spectrum of human emotions due to the inherent complexity of emotional expressions and the limited coverage of existing emotion labels. To address this, we propose a …

A Multi-scale Feature Learning Network with Optical Flow Correction for Micro- and Macro-expression Spotting

2024

Recently, automatic micro-expression (ME) analysis has attracted increasing attention, since ME is a spontaneous facial expression that can truly reflect the emotional state an individual tries to conceal. As a crucial step in ME analysis, …

Photonic diffractive generators through sampling noises from scattering media

2024 · Nature Communications

Photonic computing, with potentials of high parallelism, low latency and high energy efficiency, have gained progressive interest at the forefront of neural network (NN) accelerators. However, most existing photonic computing accelerators concentrate on discriminative NNs. …

Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks

2024 · arXiv (Cornell University)

Competition-level code generation tasks pose significant challenges for current state-of-the-art large language models (LLMs). For example, on the LiveCodeBench-Hard dataset, models such as O1-Mini and O1-Preview achieve pass@1 rates of only 0.366 and 0.143, respectively. …

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak

2024 · arXiv (Cornell University)

Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking. As LLMs become more powerful, studying jailbreak methods is critical to enhancing security …

Weakly supervised deep learning-based classification for histopathology of gliomas: a single center experience

2025 · Scientific Reports

Multiple artificial intelligence systems have been created to facilitate accurate and prompt histopathological diagnosis of tumors using hematoxylin-eosin-stained slides. We aimed to investigate whether weakly supervised deep learning can aid in glioma diagnosis. We analyzed …

Evolving Hard Maximum Cut Instances for Quantum Approximate Optimization Algorithms

2025 · arXiv (Cornell University)

Variational quantum algorithms, such as the Recursive Quantum Approximate Optimization Algorithm (RQAOA), have become increasingly popular, offering promising avenues for employing Noisy Intermediate-Scale Quantum devices to address challenging combinatorial optimization tasks like the maximum cut …

MIT: A Multi-Tower Information Transfer Framework Based on Hierarchical Task Relationship Modeling

2025

With the advancement of e-commerce platforms and online recommendation systems, conversion objectives have evolved from singular to diverse goals. To simultaneously enhance the performance of multiple conversion objectives, multi-task learning has become a classic solution. …

Transfer Learning of Surrogate Models via Domain Affine Transformation Across Synthetic and Real-World Benchmarks

2025

Surrogate models are frequently employed as efficient substitutes for the costly execution of real-world processes. However, constructing a high-quality surrogate model often demands extensive data acquisition. A solution to this issue is to transfer pre-trained …

AdaptedNorm: An Adaptive Modeling Strategy for Graph Convolutional Network-Based Deep Learning Tasks

2025 · IEEE Access

Graph neural networks (GNNs), particularly graph convolutional networks (GCNs), have demonstrated remarkable success in modeling graph-structured data across diverse applications. A critical yet underexplored aspect of GCN design lies in graph representation normalization, where the …

RASD: Retrieval-Augmented Speculative Decoding

2025 · arXiv (Cornell University)

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model structures to generate draft …

Towards Optimal Rack-scale µs-level CPU Scheduling through In-Network Workload Shaping

2025 · Rare & Special e-Zone (The Hong Kong University of Science and Technology)

>Rack-scale CPU scheduling has emerged as a promising direction to accommodate the increasing demands for microsecond-level services. However, prior work suffers from both inaccurate load balancing in the network and complex yet sub-optimal scheduling within …

Collaborative Deep Learning for Recommender Systems

2015

Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation. …

Adapting to User Interest Drift for POI Recommendation

2016 · IEEE Transactions on Knowledge and Data Engineering

Point-of-Interest recommendation is an essential means to help people discover attractive locations, especially when people travel out of town or to unfamiliar regions. While a growing line of research has focused on modeling user geographical …

Learning Graph-based POI Embedding for Location-based Recommendation

2016

With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LBSNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). …

Spatial-Aware Hierarchical Collaborative Deep Learning for POI Recommendation

2017 · IEEE Transactions on Knowledge and Data Engineering

Point-of-interest (POI) recommendation has become an important way to help people discover attractive and interesting places, especially when they travel out of town. However, the extreme sparsity of user-POI matrix and cold-start issues severely hinder …

Exploiting POI-Specific Geographical Influence for Point-of-Interest Recommendation

2018

Point-of-interest (POI) recommendation, i.e., recommending unvisited POIs for users, is a fundamental problem for location-based social networks. POI recommendation distinguishes itself from traditional item recommendation, e.g., movie recommendation, via geographical influence among POIs. Existing methods …

Neural Memory Streaming Recommender Networks with Adversarial Training

2018

With the increasing popularity of various social media and E-commerce platforms, large volumes of user behaviour data (e.g., user transaction data, rating and review data) are being continually generated at unprecedented and ever-increasing scales. It …