Zhenyu Li
6 papers in the PaperMetrix corpus
Papers by this author
-
End-to-End Mandarin Recognition based on Convolution Input
2018 · MATEC Web of Conferences
The cross-entropy criterion of mainstream neural network training is to classify and optimize each frame of acoustic data, while the continuous speech recognition uses the sequence-level transcription accuracy as a performance measure. In view of …
-
Examination of WAN traffic characteristics in a large-scale data center network
2021
Large cloud service providers have built an increasing number of geo-distributed data centers (DCs) connected by WAN to host their diverse services. While we have seen a large body of work on traffic engineering of …
-
Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modeling
2022
Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a single document. One major challenge of DocRE is to dig decisive details regarding a specific entity pair from long text. However, in …
-
UniMem: Towards a Unified View of Long-Context Large Language Models
2024 · arXiv (Cornell University)
Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-context processing ability of LLMs, they are developed in an isolated …
-
FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering
2024 · Proceedings of the AAAI Conference on Artificial Intelligence
Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users. Unfortunately, the performance of …
-
Crowdsourcing Framework for Security Testing and Verification of Industrial Cyber-Physical Systems
2025 · Sensors
With the widespread deployment of Industrial Cyber-Physical Systems (ICPS), their inherent vulnerabilities have increasingly exposed them to sophisticated cybersecurity threats. Although existing protective mechanisms can block attacks at runtime, the risk of defense failure remains. …