Wei Feng

Anonymous Authentication for Trustworthy Pervasive Social Networking

2015 · IEEE Transactions on Computational Social Systems

Pervasive social networking (PSN) supports instant social activities anywhere and at any time with the support of heterogeneous networks. In order to preserve privacy and achieve trustworthy PSN, anonymous authentication on node trust is expected …

A Bias Compensation Strategy for Wheeled Mobile Robot Odometric Self-localization Algorithm

2018 · 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS)

In service robot applications, the automated in-door mobile robot should be able to localize itself by the equipped sensor measurements. This paper is concerned with the wheeled mobile robot self-localization using the digital compass and …

Controllable Switching between Superradiant and Subradiant States in a 10-qubit Superconducting Circuit

2020 · Physical Review Letters

Superradiance and subradiance concerning enhanced and inhibited collective radiation of an ensemble of atoms have been a central topic in quantum optics. However, precise generation and control of these states remain challenging. Here we deterministically …

Semi-Supervised Clustering with Contrastive Learning for Discovering New Intents

2022 · arXiv (Cornell University)

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most scenarios …

Hierarchical Prompt Tuning for Few-Shot Multi-Task Learning

2023

Prompt tuning has enhanced the performance of Pre-trained Language Models for multi-task learning in few-shot scenarios. However, existing studies fail to consider that the prompts among different layers in Transformer are different due to the …

SEGMENT+: Long Text Processing with Short-Context Language Models

2024 · arXiv (Cornell University)

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks, such as …

The effectiveness evaluation of industry education integration model for applied universities under back propagation neural network

2025 · Scientific Reports

As the education field continues to advance, industry-education integration has become a crucial strategy for enhancing teaching quality in applied universities. This study investigates how artificial intelligence, specifically the back propagation neural network (BPNN), can …