Wenyu Chen
YOU?
Author Swipe
View article: Reinforcement Learning with Rubric Anchors
Reinforcement Learning with Rubric Anchors Open
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…
View article: Research on Financial Stock Market Prediction Based on the Hidden Quantum Markov Model
Research on Financial Stock Market Prediction Based on the Hidden Quantum Markov Model Open
Quantum finance, as a key application scenario of quantum computing, showcases multiple significant advantages of quantum machine learning over traditional machine learning methods. This paper first aims to overcome the limitations of the …
View article: Assisted-Value Factorization with Latent Interaction in Cooperate Multi-Agent Reinforcement Learning
Assisted-Value Factorization with Latent Interaction in Cooperate Multi-Agent Reinforcement Learning Open
With the development of value decomposition methods, multi-agent reinforcement learning (MARL) has made significant progress in balancing autonomous decision making with collective cooperation. However, the collaborative dynamics among age…
View article: Zero-Trust Medical Image Sharing: A Secure and Decentralized Approach Using Blockchain and the IPFS
Zero-Trust Medical Image Sharing: A Secure and Decentralized Approach Using Blockchain and the IPFS Open
The secure and efficient storage and sharing of medical images have become increasingly important due to rising security threats and performance limitations in existing healthcare systems. Centralized systems struggle to provide adequate p…
View article: TGP: Two-modal occupancy prediction with 3D Gaussian and sparse points for 3D Environment Awareness
TGP: Two-modal occupancy prediction with 3D Gaussian and sparse points for 3D Environment Awareness Open
3D semantic occupancy has rapidly become a research focus in the fields of robotics and autonomous driving environment perception due to its ability to provide more realistic geometric perception and its closer integration with downstream …
View article: Graph-to-Text Generation with Bidirectional Dual Cross-Attention and Concatenation
Graph-to-Text Generation with Bidirectional Dual Cross-Attention and Concatenation Open
Graph-to-text generation (G2T) involves converting structured graph data into natural language text, a task made challenging by the need for encoders to capture the entities and their relationships within the graph effectively. While trans…
View article: Double Distillation Network for Multi-Agent Reinforcement Learning
Double Distillation Network for Multi-Agent Reinforcement Learning Open
Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to cumulati…
View article: Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning
Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning Open
The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, due to the representational limitations of traditional monotonic value decomposition methods, …
View article: Df-Bev:Improving Bird’S-Eye-View Feature by Depth Refinement and Multi-Frame Adaptive Fusion for Multi-View Three-Dimensional Object Detection
Df-Bev:Improving Bird’S-Eye-View Feature by Depth Refinement and Multi-Frame Adaptive Fusion for Multi-View Three-Dimensional Object Detection Open
View article: RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions Open
Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover limited RAG scenarios…
View article: DecoStrat: Leveraging the Capabilities of Language Models in D2T Generation via Decoding Framework
DecoStrat: Leveraging the Capabilities of Language Models in D2T Generation via Decoding Framework Open
Current language models have achieved remarkable success in NLP tasks. Nonetheless, individual decoding methods face difficulties in realizing the immense potential of these models. The challenge is primarily due to the lack of a decoding …
View article: The Three Main Logic of the Reform of Catering Major in Higher Vocational Colleges Integrating Curriculum Ideological and Political Education under the Perspective of Industry-University-Research Collaborative Education
The Three Main Logic of the Reform of Catering Major in Higher Vocational Colleges Integrating Curriculum Ideological and Political Education under the Perspective of Industry-University-Research Collaborative Education Open
In the context of the deepening of vocational education reform and integration of industry and education in the new era, the ideological and political construction of catering courses in higher vocational colleges has become an important p…
View article: MuTCELM: An optimal multi-TextCNN-based ensemble learning for text classification
MuTCELM: An optimal multi-TextCNN-based ensemble learning for text classification Open
Feature extraction plays a critical role in text classification, as it converts textual data into numerical representations suitable for machine learning models. A key challenge lies in effectively capturing both semantic and contextual in…
View article: A robust algorithm for authenticated health data access via blockchain and cloud computing
A robust algorithm for authenticated health data access via blockchain and cloud computing Open
In modern healthcare, providers increasingly use cloud services to store and share electronic medical records. However, traditional cloud hosting, which depends on intermediaries, poses risks to privacy and security, including inadequate c…
View article: A Compressive Memory-based Retrieval Approach for Event Argument Extraction
A Compressive Memory-based Retrieval Approach for Event Argument Extraction Open
Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap b…
View article: Accelerated Markov Chain Monte Carlo Using Adaptive Weighting Scheme
Accelerated Markov Chain Monte Carlo Using Adaptive Weighting Scheme Open
Gibbs sampling is one of the most commonly used Markov Chain Monte Carlo (MCMC) algorithms due to its simplicity and efficiency. It cycles through the latent variables, sampling each one from its distribution conditional on the current val…
View article: Unified Training for Cross-Lingual Abstractive Summarization by Aligning Parallel Machine Translation Pairs
Unified Training for Cross-Lingual Abstractive Summarization by Aligning Parallel Machine Translation Pairs Open
Cross-lingual summarization (CLS) is essential for enhancing global communication by facilitating efficient information exchange across different languages. However, owing to the scarcity of CLS data, recent studies have employed multi-tas…
View article: Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction Open
Recent mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring the correlations among multiple events. To address these limitations, here we propose a multiple-event arg…
View article: Pre-Trained Transformer-Based Models for Text Classification Using Low-Resourced Ewe Language
Pre-Trained Transformer-Based Models for Text Classification Using Low-Resourced Ewe Language Open
Despite a few attempts to automatically crawl Ewe text from online news portals and magazines, the African Ewe language remains underdeveloped despite its rich morphology and complex "unique" structure. This is due to the poor quality, unb…
View article: Multichannel 2D-CNN Attention-Based BiLSTM Method for Low-Resource Ewe Sentiment Analysis
Multichannel 2D-CNN Attention-Based BiLSTM Method for Low-Resource Ewe Sentiment Analysis Open
The unavailability of an annotated dataset for a low-resource Ewe language makes it difficult to develop an automated system to appropriately evaluate public opinion on events, news, policies, and regulations. In this study, we collected a…
View article: Multi-feature concatenation and multi-classifier stacking: an interpretable and generalizable machine learning method for MDD discrimination with rsfMRI
Multi-feature concatenation and multi-classifier stacking: an interpretable and generalizable machine learning method for MDD discrimination with rsfMRI Open
Major depressive disorder is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is inc…
View article: Adaptive Textual Label Noise Learning based on Pre-trained Models
Adaptive Textual Label Noise Learning based on Pre-trained Models Open
The label noise in real-world scenarios is unpredictable and can even be a mixture of different types of noise. To meet this challenge, we develop an adaptive textual label noise learning framework based on pre-trained models, which consis…
View article: Multi-Channel 2D-CNN And Attention-Based BiLSTM Method for Sentiment Analysis on Low-Resource Ewe Language
Multi-Channel 2D-CNN And Attention-Based BiLSTM Method for Sentiment Analysis on Low-Resource Ewe Language Open
The unavailability of annotated dataset for a low-resource Ewe language makes it difficult to develop an automated system to appropriately evaluate public opinion on events, news, policies, and regulations in the language. In this study, w…
View article: Noise-Regularized Advantage Value for Multi-Agent Reinforcement Learning
Noise-Regularized Advantage Value for Multi-Agent Reinforcement Learning Open
Leveraging global state information to enhance policy optimization is a common approach in multi-agent reinforcement learning (MARL). Even with the supplement of state information, the agents still suffer from insufficient exploration in t…
View article: Eliminating Gradient Conflict in Reference-based Line-Art Colorization
Eliminating Gradient Conflict in Reference-based Line-Art Colorization Open
Reference-based line-art colorization is a challenging task in computer vision. The color, texture, and shading are rendered based on an abstract sketch, which heavily relies on the precise long-range dependency modeling between the sketch…
View article: Incorporating Siamese Network Structure into Graph Neural Network
Incorporating Siamese Network Structure into Graph Neural Network Open
Siamese network plays an important role in many artificial intelligence domains, but there requires more exploration of applying Siamese structure to graph neural network. This paper proposes a novel framework that incorporates Siamese net…
View article: DPGNN: Dual-Perception Graph Neural Network for Representation Learning
DPGNN: Dual-Perception Graph Neural Network for Representation Learning Open
Graph neural networks (GNNs) have drawn increasing attention in recent years and achieved remarkable performance in many graph-based tasks, especially in semi-supervised learning on graphs. However, most existing GNNs are based on the mess…
View article: Encryption Based Image Watermarking Algorithm in 2DWT-DCT Domains
Encryption Based Image Watermarking Algorithm in 2DWT-DCT Domains Open
This paper proposes an encryption-based image watermarking scheme using a combination of second-level discrete wavelet transform (2DWT) and discrete cosine transform (DCT) with an auto extraction feature. The 2DWT has been selected based o…
View article: Self-Paced Two-dimensional PCA
Self-Paced Two-dimensional PCA Open
Two-dimensional PCA (2DPCA) is an effective approach to reduce dimension and extract features in the image domain. Most recently developed techniques use different error measures to improve their robustness to outliers. When certain data p…
View article: Bioinformatics and system biology approach to identify the influences of SARS-CoV-2 infections to idiopathic pulmonary fibrosis and chronic obstructive pulmonary disease patients
Bioinformatics and system biology approach to identify the influences of SARS-CoV-2 infections to idiopathic pulmonary fibrosis and chronic obstructive pulmonary disease patients Open
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), better known as COVID-19, has become a current threat to humanity. The second wave of the SARS-CoV-2 virus has hit many countries, and the confirmed COVID-19 cases are quick…