Zheng Wang

Intelligent multimedia communications platform based on IMS

2016

IP Multimedia Subsystem (IMS) was the core technology of next generation networks. Intelligent multimedia communications platform which based on IMS was established by Henan Power. It integrated video conferencing, teleconferencing and data collaboration. It also …

RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-Imbalanced Labels for Network Embedding

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised …

Jointly Learning Entity and Relation Representations for Entity Alignment

2019

Yuting Wu, Xiao Liu, Yansong Feng, Zheng Wang, Dongyan Zhao. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Model Rectification via Unknown Unknowns Extraction from Deployment Samples

2021 · arXiv (Cornell University)

Model deficiency that results from incomplete training data is a form of structural blindness that leads to costly errors, oftentimes with high confidence. During the training of classification tasks, underrepresented class-conditional distributions that a given …

Spectrum Gaussian Processes Based On Tunable Basis Functions

2021 · arXiv (Cornell University)

Spectral approximation and variational inducing learning for the Gaussian process are two popular methods to reduce computational complexity. However, in previous research, those methods always tend to adopt the orthonormal basis functions, such as eigenvectors …

Physical Adversarial Attack meets Computer Vision: A Decade Survey

2022 · arXiv (Cornell University)

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision, their vulnerability to adversarial attacks remains a critical concern. Extensive research has demonstrated that incorporating sophisticated perturbations into input images can lead to …

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations

2021 · arXiv (Cornell University)

Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an …

Dynamic impairment classification through arrayed comparisons

2022 · Statistics in Medicine

The multivariate normative comparison (MNC) method has been used for identifying cognitive impairment. When participants' cognitive brain domains are evaluated regularly, the longitudinal MNC (LMNC) has been introduced to correct for the intercorrelation among repeated …

FedGS: Federated Graph-based Sampling with Arbitrary Client Availability

2022 · arXiv (Cornell University)

While federated learning has shown strong results in optimizing a machine learning model without direct access to the original data, its performance may be hindered by intermittent client availability which slows down the convergence and …

SADA: Self-Adaptive Domain Adaptation From Black-Box Predictors

2024

Domain adaptation from black-box predictors aims to perform domain adaptation using predictions from a model trained on the source domain, thereby avoiding privacy issues associated with source domain data and enabling the training of a …

A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models

2024

Due to the continuous emergence of new data, version updates have become an indispensable requirement for Large Language Models (LLMs).The training paradigms for version updates of LLMs include pre-training from scratch (PTFS) and continual pre-training …

Controlled quantum secure direct communication with twice identity authentications based on the entanglement swapping of Bell states

2025 · Laser Physics Letters

Abstract In this paper, after quantum identity authentication is applied into controlled quantum secure direct communication (CQSDC), a CQSDC protocol with twice identity authentications is put forward based on the entanglement swapping of Bell states. …

PSCon: Product Search Through Conversations

2025

Conversational Product Search ( CPS ) systems interact with users via natural language to offer personalized and context-aware product lists. However, most existing research on CPS is limited to simulated conversations, due to the lack …

MS-RAG: A Multimodal Retrieval-Augmented Framework for Digital Twins with Knowledge Graph Reasoning

2025

Traditional Retrieval-Augmented Generation (RAG) frameworks struggle to effectively handle multi-source heterogeneous data in digital twin scenarios, leading to insufficient accuracy in component relationship analysis and fault reasoning. This paper proposes a Multi-Stage Retrieval-Augmented Framework (MS-RAG), …

S2-Boost: Synergistic Semantic Boosting for Coarse-to-Fine Ensemble Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Neuroscientific evidence reveals that human visual recognition is not an instantaneous event but a hierarchical process, where the brain constructs a holistic perception by progressively integrating simple features like edges or texture into complex scenes. …