Yue Wang

Dynamic Graph CNN for Learning on Point Clouds

2019 · ACM Transactions on Graphics

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been …

An improved collaborative filtering recommendation algorithm not based on item rating

2015

As e-commerce grows fast nowadays, recommender systems have become an integral part of every electricity business. A number of the recommendation algorithms need score matrix (i.e., matrix that is used to record the data of …

Public Cloud Security Protection Research

2019

With the rapid development of cloud computing, public cloud as the main form, the attack value is higher, and security is more difficult. This paper expounds the background and concept of public cloud. Starting from …

Joint Feature-level and Pixel-level Domain Adaption for Object Detection in the Wild

2019

The obeject detector trained on a source dataset probablely fails to be generalized well to a target dataset due to the domian shift between different distributions. This paper aims at reducing such domain gap without …

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

2020

Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction. However, few existing works excel in solving the overlapping triple problem where multiple relational triples in the same sentence share the same …

Interference at the single-photon level based on silica photonics robust against channel disturbance

2020 · Photonics Research

Quantum key distribution (QKD) provides a solution for communication of unconditional security. However, the quantum channel disturbance in the field severely increases the quantum bit-error rate, degrading the performance of a QKD system. Here we …

Enabling Role-Based Orchestration for Cloud Applications

2021 · Applied Sciences

With the rapidly growing popularity of cloud services, the cloud computing faces critical challenges to orchestrate the deployment and operation of cloud applications on heterogenous cloud platforms. Cloud applications are built on a platform model …

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Pre-trained models for Natural Languages (NL) like BERT and GPT have been recently shown to transfer well to Programming Languages (PL) and largely benefit a broad set of code-related tasks. Despite their success, most current …

A Trigger Exploration Method for Backdoor Attacks on Deep Learning-Based Traffic Control Systems

2021 · 2021 60th IEEE Conference on Decision and Control (CDC)

Deep learning methods are in the forefront of techniques used to perform complex controls in autonomous vehicles (AVs). Such methods are vulnerable to nuanced types of adversarial attacks, and can have sever safety implications. Specifically, …

Research on Intelligent Question Answering System under Operation and Maintenance Knowledge Graph

2022

At present, many intelligent question answering based on knowledge graphs can answer simple questions, but there is no good solution to complex multi-hop problems. In response to this, relying on the knowledge graph of the …

The Construction Techniques of Artificial Intelligence Hierarchical Dataset in Power Industry

2022 · 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)

Artificial intelligence datasets now are common in power electric companies for their own research work. Many Artificial Intelligence research are data-driven and require large amount of data. A single company's dataset only contains quite limited …

GRAFS: Graphical Faceted Search System to Support Conceptual Understanding in Exploratory Search

2023 · arXiv (Cornell University)

When people search for information about a new topic within large document collections, they implicitly construct a mental model of the unfamiliar information space to represent what they currently know and guide their exploration into …

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

2023 · arXiv (Cornell University)

Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or collisions. Backdoor functionality is typically incorporated by contaminating training …

Regularized Adaptive Huber Matrix Regression and Distributed Learning

2023 · Statistica Sinica

Matrix regression provides a powerful technique for analyzing matrixtype data, as exemplified by many contemporary applications. Despite the rapid advance, distributed learning for robust matrix regression to deal with heavy-tailed noises in the big data …

Multiferroic Magnon Spin-Torque Based Reconfigurable Logic-In-Memory

2023 · arXiv (Cornell University)

Magnons, bosonic quasiparticles carrying angular momentum, can flow through insulators for information transmission with minimal power dissipation. However, it remains challenging to develop a magnon-based logic due to the lack of efficient electrical manipulation of …

A Superalignment Framework in Autonomous Driving with Large Language Models

2024

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased remarkable …

HA-SCN: Learning Hierarchical Aligned Subtree Convolutional Networks for Graph Classification

2024

In this paper, we propose a Hierarchical Aligned Subtree Convolutional Network (HA-SCN) for graph classification. Our idea is to transform graphs of arbitrary sizes into fixed-sized aligned graphs and construct a normalized K-layer m-ary subtree …

Understanding the Effects of Explaining Predictive but Unintuitive Features in Human-XAI Interaction

2025

Feature importance explanation, which highlights input features that are most influential to the output, is a popular explainable AI (XAI) technique to help users understand machine learning model predictions.However, features deemed predictive by machines can …

DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management

2025 · arXiv (Cornell University)

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches usually rely on handcrafted rule-based reward functions. However, …

Multi-source domain adaptation method based on domain similarity for tool wear states identification

2026 · Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture

Single source domain transfer learning has been used in the field of tool wear states monitoring. However, this method ignores the case of transfer learning from multiple source domains and it is unreasonable to transfer …

VO ₂ Nanoparticle‐Densely Packed Microwires for Flexible and Energy‐Efficient Photonic Synapses in Neuromorphic Computing

2026 · Laser & Photonics Review

ABSTRACT The growing demand for brain‐inspired computing in wearable electronics necessitates systems with high mechanical stability, biocompatibility, and low‐power processing. However, most existing neuromorphic technologies suffer from limited flexibility, reliance on ultraviolet light, and high …

Theoretical research and practical exploration of a new model for cultivating top pharmaceutical engineering talent in the new era

2026 · Industry and Higher Education

Against the background of deepening higher education reform, traditional pharmaceutical engineering education fails to match modern industrial demands for innovation, social responsibility, and industry-adapted competencies. This study constructs an integrated talent cultivation framework that merges …

<tt>SemAder</tt> : Evading LLM-Based Binary Code Analysis via Structure-Semantics Joint Induction

2026 · ACM Transactions on Privacy and Security

With the rapid advancement of artificial intelligence (AI), particularly the widespread adoption of large language models (LLMs) in code comprehension and analysis, their strong semantic parsing capabilities have introduced new threats to software security. Attackers …

Privacy-Preserving Transaction Admission with Warrant-Based Trace Recovery for Regulated Cryptocurrency Transactions

2026 · Electronics

Public blockchain transactions need compliance support without exposing stable identity anchors. This paper presents a privacy-preserving transaction admission framework for regulated cryptocurrency transaction paths. It adds an admission and recovery layer to admission-aware applications, contracts, …

Safety-Constrained Deep Reinforcement Learning for Source–Load–Storage Coordinated Operation of Green Low-Carbon Data Centers

2026 · Energies

Green low-carbon data centers operate as coupled cyber-energy systems whose dispatch must coordinate renewable generation, grid exchange, battery storage, cooling load, flexible computing workload, carbon-intensity signals, and reliability constraints. This study develops and evaluates a …

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

2023

Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations. First, they often adopt a specific architecture (encoder-only or decoder-only) or …