Kun Wang

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 …

MiFlO: A scheduling algorithm based on mice flows optimization in hybrid data center network

2017

With the rapid development of cloud computing and emerging services, traffic in data center network is experiencing an explosive growth, which has brought a great challenge to the existing electrical data center networks. In order …

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 …

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one …

An Effective Crop-Paste Pipeline for Few-shot Object Detection

2023 · arXiv (Cornell University)

Few-shot object detection (FSOD) aims to expand an object detector for novel categories given only a few instances for training. However, detecting novel categories with only a few samples usually leads to the problem of …

Device-Performance-Driven Heterogeneous Multiparty Learning for Arbitrary Images

2023 · IEEE Transactions on Neural Networks and Learning Systems

Multiparty learning (MPL) is an emerging framework for privacy-preserving collaborative learning. It enables individual devices to build a knowledge-shared model and remaining sensitive data locally. However, with the continuous increase of users, the heterogeneity gap …

OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models

2023 · arXiv (Cornell University)

Information Technology (IT) Operations (Ops), particularly Artificial Intelligence for IT Operations (AIOps), is the guarantee for maintaining the orderly and stable operation of existing information systems. According to Gartner's prediction, the use of AI technology …

Reinforcement Learning with Decoupled State Representation for Robot Manipulations

2024 · Neural Processing Letters

Abstract Deep reinforcement learning has significantly advanced robot manipulations by providing an alternative solution for designing control strategies using raw images as direct inputs. While images offer additional environmental information, the end-to-end policy training manner …

On the Role of Attention Heads in Large Language Model Safety

2024 · arXiv (Cornell University)

Large language models (LLMs) achieve state-of-the-art performance on multiple language tasks, yet their safety guardrails can be circumvented, leading to harmful generations. In light of this, recent research on safety mechanisms has emerged, revealing that …

Discovering Latent Causal Graphs from Spatiotemporal Data

2024 · arXiv (Cornell University)

Many important phenomena in scientific fields like climate, neuroscience, and epidemiology are naturally represented as spatiotemporal gridded data with complex interactions. Inferring causal relationships from these data is a challenging problem compounded by the high …

Optimal design of data processing and data encryption detection and identification algorithm for engineering risk points based on machine learning

2024

With the increasing scale and complexity of engineering projects, engineering audit is facing increasingly severe challenges in data processing and data encryption detection and identification of risk points. The purpose of this paper is to …

Quantum memory assisted entangled state verification with local measurements

2025 · Physical Review Research

We consider the quantum memory assisted quantum state verification task, where an adversary prepares independent multipartite entangled states and sends them to the local verifiers, who then store several copies in the quantum memory and …

RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework

2025

Recent advances of large language models in the field of Verilog generation have raised several ethical and security concerns, such as code copyright protection and dissemination of malicious code. Researchers have employed watermarking techniques to …

Comparative Evaluation of Large Reasoning Models and Large Language Models in Radiation Oncology: Performance in Nasopharyngeal Carcinoma-Related Queries (Preprint)

2025

<sec> <title>BACKGROUND</title> Large language models (LLMs), such as ChatGPT-4, have demonstrated potential in supporting medical decision-making but remain limited in scenarios requiring subjective judgment and complex clinical reasoning. Emerging large reasoning models (LRMs), including DeepSeek-R1 …

Design of intelligent proofreading system for English translation based on CNN and BERT

2025 · arXiv (Cornell University)

Since automatic translations can contain errors that require substantial human post-editing, machine translation proofreading is essential for improving quality. This paper proposes a novel hybrid approach for robust proofreading that combines convolutional neural networks (CNN) …

A Vision for Auto Research with LLM Agents

2025 · arXiv (Cornell University)

This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the …

Distributed quantum inner product estimation with structured random circuits

2026 · npj Quantum Information

Distributed inner product estimation (DIPE) is a fundamental task in quantum information, aiming to estimate the inner product between two unknown quantum states prepared on distributed quantum platforms. Existing rigorous sample complexity analyses are limited …

Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

As Audio Large Language Models (ALLMs) emerge as powerful tools for speech processing, their safety implications demand urgent attention. While considerable research has explored textual and vision safety, audio’s distinct characteristics present significant challenges. This …