Ying Zhang
16 papers in the PaperMetrix corpus
Papers by this author
-
Research on Test Method of Domestic Embedded Multi-core Operating System
2016
Based on domestic embedded multi-core operating system testing, this paper describes the characteristics of the multi-core operating system and existing test contents and gives an effective software function and performance function test method for application …
-
Design and Practice of Introduction to Basic Courses of Mathematical-Physics Science
2018 · Proceedings of the 2018 2nd International Conference on Management, Education and Social Science (ICMESS 2018)
Advanced Mathematics, College Physics, and Engineering Mechanics are basic courses of Mathematicalphysics science that set up by college of science for all the college students. These courses are the basis for specialized course learning and …
-
A Power Forecasting Approach for PV Plant based on Irradiance Index and LSTM
2018
A novel power forecasting approach for PV plant based on irradiance index and LSTM is presented in this paper. Firstly, we come up with a clustering algorithm according to the irradiance index after analyzing the …
-
Infusing Multi-Source Knowledge with Heterogeneous Graph Neural Network for Emotional Conversation Generation
2021 · Proceedings of the AAAI Conference on Artificial Intelligence
The success of emotional conversation systems depends on sufficient perception and appropriate expression of emotions. In a real-world conversation, we firstly instinctively perceive emotions from multi-source information, including the emotion flow of dialogue history, facial …
-
An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization
2021
Baohang Zhou, Xiangrui Cai, Ying Zhang, Xiaojie Yuan. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
-
Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition
2021
Zero-resource named entity recognition (NER) severely suffers from data scarcity in a specific domain or language. Most studies on zero-resource NER transfer knowledge from various data by fine-tuning on different auxiliary tasks. However, how to …
-
Target Tracking Method Based on Information Matrix for Multi-sensor Data Fusion
2022
Smart driving technology has great potential to improve traffic safety, traffic efficiency, and driving experience. So, it is a hot topic for current and future research in the field of intelligent transportation. However, the future …
-
Complex Question Enhanced Transfer Learning for Zero-Shot Joint Information Extraction
2023 · IEEE/ACM Transactions on Audio Speech and Language Processing
Zero-shot information extraction (IE) tasks have attracted great attention recently. However, how to jointly model multiple IE tasks in the zero-shot scenario is still an open question. In this article, we focus on zero-shot joint …
-
The Cloud Model-Based Evaluation of Public Building Renewal Potential with the Game Theory Combination Weighting Methods-Case Study in China
2024 · Preprints.org
Currently, urban renewal activities in China are booming. And promoting the renovation of public buildings is the key due to its large scale, high cost and significant impact to the nature and social environment. To …
-
Rail-only: A Low-Cost High-Performance Network for Training LLMs with Trillion Parameters
2024
This paper presents a low-cost network architecture for training large language models (LLMs) at hyperscale. We study the optimal parallelization strategy of LLMs and propose a novel datacenter network design tailored to LLM's unique communication …
-
Online Prediction Product Control Based on Information-Aware Weight and Error Compensation
2024
This paper applies the information-aware weight method to the field of engineering where the validity of the data characteristics of the prediction object fluctuates or changes rapidly within a limited range. It clarifies the relationship …
-
MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training
2025
Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named experts, on a per-token basis. This gated computation generates dynamic communications that cannot be determined beforehand, challenging the existing GPU interconnects that remain …
-
On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing
2025 · Proceedings of the VLDB Endowment
Missing data imputation, which aims to impute the missing values in the raw datasets, is crucial for modern data-driven models like large language models (LLMs). Despite its importance, existing solutions either 1) only support numerical …
-
Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
2025 · arXiv (Cornell University)
While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall via unseen queries remain poorly understood. Common two-stage training strategies, which sequentially train on fact …
-
Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs
2025 · arXiv (Cornell University)
Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches, both of which encode textual …
-
A large language model for electronic health records
2022 · npj Digital Medicine
There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI …