Yi Liu

Chinese syllable-to-character conversion with recurrent neural network based supervised sequence labelling

2015

Chinese Syllable-to-Character (S2C) conversion is the important component for Input Methods, and the key problem in Chinese S2C conversion is the serious phenomenon in Chinese language. In order to disambiguate homophones to improve Chinese S2C …

Local Enhanced Catfish Bat Algorithm

2016

To resolve the conflict between convergence speed and diversity in Bat Algorithm (BA), we propose a novel improved BA algorithm called local enhanced catfish bat algorithm (LECBA). In LECBA, some inferior bats of initial population …

An Intelligent Matching Algorithm of CDCI Model

2018

This paper aims to study the intelligent recommendation algorithm and Crowd-designing Clothing Industry (CDCI) model to propose a new intelligent matching algorithm called CDCI-matching algorithm and correspondingly improve the CDCI model. The algorithm draws on …

Investigating the Stacked Phonetic Bottleneck Feature for Speaker Verification with Short Voice Commands

2017

Text-dependent speaker verification (SV) with short voice command (SV-SVC) has increasing demand in many applications. Different from conventional SV, SV-SVC usually uses short fixed voice commands for user-friendly purpose, which causes technical challenges compared with …

Outlier-Robust Schmidt-Kalman Filter Using Variational Inference

2020

The Schmidt-Kalman filter (SKF) achieves filtering consistency in the presence of biases in system dynamic and measurement models through accounting for their impacts when updating the state estimate and covariance. However, the performance of the …

Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm.

2021 · arXiv (Cornell University)

Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the whole distribution of the total return rather than only its expectation. Despite the remarkable performance of distributional RL, a theoretical understanding of its …

Stable feature selection based on brain storm optimisation for high‐dimensional data

2021 · Electronics Letters

Abstract Feature selection is a widely used data pre‐processing method. However, the research on feature selection stability is very rare. Although there are some related studies that mainly focus on filters rather than wrappers, especially …

Tutorial: A Lightweight Web Application for Software Vulnerability Demonstration

2021

In cybersecurity education, it is critical to introduce students to security concepts and keep them aware of common software security weaknesses. However, the effectiveness of delivering such knowledge is complicated by the lack of practical …

Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

2022 · IEEE Transactions on Dependable and Secure Computing

Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only …

A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling

2022

Automatic speech recognition (ASR) systems used on smart phones or vehiclesare usually required to process speech queries from very different domains.In such situations,a vanilla ASR system usually fails to perform well on every domain.This paper …

Evolutionary Action Selection for Gradient-based Policy Learning

2022 · arXiv (Cornell University)

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation.The evolutionary part in these hybrid methods maintains a population of …

FaaSLight: General Application-Level Cold-Start Latency Optimization for Function-as-a-Service in Serverless Computing

2022 · arXiv (Cornell University)

Serverless computing is a popular cloud computing paradigm that frees developers from server management. Function-as-a-Service (FaaS) is the most popular implementation of serverless computing, representing applications as event-driven and stateless functions. However, existing studies report …

Comparative Analysis of Applying Imputation and Hyperparameter Optimization in Cancer Diagnosis

2023 · Research Square

Abstract Cancer is one of the leading causes for death worldwide, accurate and timely detection of cancer can save lives. With more machine learning algorithms and approaches have been applied in cancer diagnosis, there is …

GLDAP: Global Dynamic Action Persistence Adaptation for Deep Reinforcement Learning

2023 · ACM Transactions on Autonomous and Adaptive Systems

In the implementation of deep reinforcement learning (DRL), action persistence strategies are often adopted so agents maintain their actions for a fixed or variable number of steps. The choice of the persistent duration for agent …

Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter

2023

Federated Multilingual Neural Machine Translation (Fed-MNMT) has emerged as a promising paradigm for institutions with limited language resources. This approach allows multiple institutions to act as clients and train a unified model through model synchronization, …

Towards Flow Scheduling in A Quantum Data Center

2023

We propose an architecture for future quantum data centers with the scheduling of quantum computing flows, which integrates quantum processors, quantum switches, and quantum networks. The versatility of these data centers is discussed, highlighting their …

ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers

2023

The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility of ASR …

A Combined Approach of Program Analysis and Deep Learning for Code Completion

2024 · Scientific Journal of Technology

Code completion, a critical feature in integrated development environments, significantly reduces the coding workload for developers. Traditional code completion techniques often focus on the natural language properties of code, overlooking the structural characteristics of programming …

Research on the Measures to Promote the Teaching Reform of Biochemical Laboratory by Using National Experimental Skills

2024 · Modern management science & engineering.

Biochemical examination, as the core course of medical laboratory technology specialty, is highly applied and practical, so it is particularly critical to cultivate students' ability in this specialty. As an important platform to improve the …

Multivariate Data Governance Method for Civil Aviation Air Defense Security Supervision

2025

With the rapid development of the civil aviation industry, air defense and security issues are becoming increasingly complex. Data governance and decision optimization are important means to promote the scientific and precise handling of security …

Agentic memory-augmented retrieval and evidence grounding for medical question-answering tasks

2025 · medRxiv

Objective: To evaluate if a tool-using agent-based system utilizing large language models (LLMs) for medical question-answering (QA) tasks outperforms standalone LLMs. Methods: We developed a unified, open-source LLM-based agentic system that integrates document retrieval, re-ranking, …

SAP: Privacy-Preserving Fine-Tuning on Language Models with Split-and-Privatize Framework

2025

Pre-trained Language Models (PLM) have enabled a cost-effective approach to handling various downstream applications via Parameter-Efficient-Fine-Tuning (PEFT) techniques. In this context, service providers have introduced a popular fine-tuning-based product service known as Model-as-a-Service (MaaS). This …

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models

2025 · arXiv (Cornell University)

Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, …

Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network

2018

Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, Hua Wu. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.