Qi Wang

Text similarity algorithm based on semantic vector space model

2016

In this paper, a text similarity computation method named VSM-Cilin which is based on semantic vector space model is proposed in the background of radio station. VSM-Cilin improved the traditional VSM in the following areas. …

Weighted Single-Pass Fuzzy c-Means Algorithm Based on Density Peaks

2018

This paper presents an improved single-pass fuzzy c-means algorithm, which is referred to as Weighted Single-Pass Fuzzy c-Means Algorithm Based on Density Peaks (dpwSPFCM). The classical clustering methods can deal with the small-scale data problems …

SoK: TEE-Assisted Confidential Smart Contract

2022 · Proceedings on Privacy Enhancing Technologies

The blockchain-based smart contract lacks privacy, since the contract state and instruction code are exposed to the public. Combining smart-contract execution with Trusted Execution Environments provides an efficient solution, called TEE-assisted smart contracts (TCSC), for …

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning

2023 · arXiv (Cornell University)

Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the overestimation bias …

Book Rating Prediction Model Based on LightGBM and Text Convolutional Neural Network

2023

Personalized recommendation is one of the key components of efficient library services today. Most existing collaborative filtering algorithms predict ratings based on user similarity and item similarity, without considering the influence of features such as …

DRC: Discrete Representation Classifier With Salient Features via Fixed-Prototype

2024 · IEEE Transactions on Circuits and Systems for Video Technology

Image classification models including convolutional neural networks (CNN) and vision transformers (ViT) commonly employ a fully connected (FC) layer as the classifier. However, the fully connected nature of FC brings large amounts of weight parameters, …

Inbox Invasion: Exploiting MIME Ambiguities to Evade Email Attachment Detectors

2024

Email attachments have become a favored delivery vector for malware campaigns. In response, email attachment detectors are widely deployed to safeguard email security. However, an emerging threat arises when adversaries exploit parsing discrepancies between email …

An all-magnonic neuron with tunable fading memory

2025 · ArXiv.org

Magnonics offers nanometer-scale wave propagation and strong nonlinearities, making it attractive for neuromorphic applications such as artificial neurons. Yet, magnonic elements with interconnections solely within the magnonic system remain challenging, preventing the realization of interconnected …

Beyond Retraining: Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision–Language Models

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test image’s class label is drawn from a predefined label set and lack …