Hui Wang

Global ocean forecasting and scientific big data

2015 · Chinese Science Bulletin (Chinese Version)

Global ocean forecasting is one of the future priorities of marine forecasting. This is closely related to the implementation of marine strategy, maintenance of maritime rights, and development of deep sea resources, which are in …

Data‐driven modeling based on kernel extreme learning machine for sugarcane juice clarification

2019 · Food Science & Nutrition

Clarification of sugarcane juice is an important operation in the production process of sugar industry. The gravity purity and the color value of juice are the two most important evaluation indexes in the cane sugar …

Quantum Interference between Light Sources Separated by 150 Million Kilometers

2019 · Physical Review Letters

We report an experiment to test quantum interference, entanglement, and nonlocality using two dissimilar photon sources, the Sun and a semiconductor quantum dot on the Earth, which are separated by ∼150 million kilometers. By making …

U2-VC: one-shot voice conversion using two-level nested U-structure

2021 · EURASIP Journal on Audio Speech and Music Processing

Abstract Voice conversion is to transform a source speaker to the target one, while keeping the linguistic content unchanged. Recently, one-shot voice conversion gradually becomes a hot topic for its potentially wide range of applications, …

Towards Fair and Robust Classification

2022

Robustness and fairness are two equally important issues for machine learning systems. Despite the active research on robustness and fairness of ML recently, these efforts focus on either fairness or robustness, but not both. To …

Intermediate-Task Learning with Pretrained Model for Synthesized Speech MOS Prediction

2023

Mean Opinion Scores (MOS) prediction has been a crucial task for speech quality assessment. Recently, methods based on pre-training and fine-tuning achieved the start-of-the-art performance for MOS prediction. While these two-stage methods can improve the …

Chinese college students collaborative mobile-assisted language learning experience and flow as a key factor for further adoption

2023 · Frontiers in Psychology

Introduction: In recent years, the widespread shift toward online learning in higher education has led to a notable increase in the utilization of collaborative mobile-assisted language learning (MALL). However, the efficacy and implementation of MALL …

Dynamic Corrected Split Federated Learning With Homomorphic Encryption for U-Shaped Medical Image Networks

2023 · IEEE Journal of Biomedical and Health Informatics

U-shaped networks have become prevalent in various medical image tasks such as segmentation, and restoration. However, most existing U-shaped networks rely on centralized learning which raises privacy concerns. To address these issues, federated learning (FL) …

Gaussian Boson Sampling with Pseudo-Photon-Number-Resolving Detectors and Quantum Computational Advantage

2023 · Physical Review Letters

We report new Gaussian boson sampling experiments with pseudo-photon-number-resolving detection, which register up to 255 photon-click events. We consider partial photon distinguishability and develop a more complete model for the characterization of the noisy Gaussian …

COPR: Continual Human Preference Learning via Optimal Policy Regularization

2024 · arXiv (Cornell University)

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of human preferences, continual alignment becomes more crucial and practical …

Differentially Private Federated Learning: A Systematic Review

2024 · arXiv (Cornell University)

In recent years, privacy and security concerns in machine learning have promoted trusted federated learning to the forefront of research. Differential privacy has emerged as the de facto standard for privacy protection in federated learning …

Abnormal Traffic Detection Method Based on Weighted Bayesian

2024

Email has a fast dissemination speed and low cost, and has been widely used in people's daily work and study. However, the proliferation of spam emails, such as a large number of advertising emails flooding …

Chinese Medical Question Answer Matching Using End-to-End Character-Level Multi-Scale CNNs

2017 · Applied Sciences

This paper focuses mainly on the problem of Chinese medical question answer matching, which is arguably more challenging than open-domain question answer matching in English due to the combination of its domain-restricted nature and the …

S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

2020

Recently, significant progress has been made in sequential recommendation with deep learning. Existing neural sequential recommendation models usually rely on the item prediction loss to learn model parameters or data representations. However, the model trained …

PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

2021 · arXiv (Cornell University)

Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demonstrated strong performances on natural language understanding and generation with …

RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms

2021

In recent years, there are a large number of recommendation algorithms proposed in the literature, from traditional collaborative filtering to deep learning algorithms. However, the concerns about how to standardize open source implementation of recommendation …