Yuyu Luo
YOU?
Author Swipe
View article: Reinforcement Learning for Hybrid Charging Stations Planning and Operation Considering Fixed and Mobile Chargers
Reinforcement Learning for Hybrid Charging Stations Planning and Operation Considering Fixed and Mobile Chargers Open
The success of vehicle electrification relies on efficient and adaptable charging infrastructure. Fixed-location charging stations often suffer from underutilization or congestion due to fluctuating demand, while mobile chargers offer flex…
View article: TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding Open
Transformers exhibit proficiency in capturing long-range dependencies, whereas State Space Models (SSMs) facilitate linear-time sequence modeling. Notwithstanding their synergistic potential, the integration of these architectures presents…
View article: Molecular Mechanisms of the Biological Control of Pine Wilt Disease Using Microorganisms
Molecular Mechanisms of the Biological Control of Pine Wilt Disease Using Microorganisms Open
Pine wilt disease (PWD), caused by the pine wood nematode (PWN, Bursaphelenchus xylophilus), poses a significant threat to global pine forests and calls for the development of innovative management strategies. Microbial control emerges as …
View article: Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking
Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking Open
Large Language Models (LLMs) have demonstrated notable capabilities across financial tasks, including financial report summarization, earnings call transcript analysis, and asset classification. However, their real-world effectiveness in m…
View article: Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights
Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights Open
Charts are crucial for data analysis and decision-making.Text-to-chart retrieval systems have become increasingly important for Business Intelligence (BI), where users need to find relevant charts that match their analytical needs. These n…
View article: Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards
Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards Open
Recent advances in large language models (LLMs) have significantly improved performance on the Text-to-SQL task by leveraging their powerful reasoning capabilities. To enhance accuracy during the reasoning process, external Process Reward …
View article: Soil Nutrient Dynamics and Fungal Community Shifts Drive the Degradation of Pinus sylvestris var. mongholica Plantations in the Loess Plateau
Soil Nutrient Dynamics and Fungal Community Shifts Drive the Degradation of Pinus sylvestris var. mongholica Plantations in the Loess Plateau Open
The degradation of Pinus sylvestris var. mongholica plantations in Youyu County on the Loess Plateau has caused major ecological issues, though the mechanisms remain poorly understood. This study explores the effects of stand age and soil …
View article: Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective
Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective Open
Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision-making remains inadequately evaluated. Current benchmarks primarily assess LLMs' understanding on …
View article: Cost-effective Missing Value Imputation for Data-effective Machine Learning
Cost-effective Missing Value Imputation for Data-effective Machine Learning Open
Given a dataset with incomplete data (e.g., missing values), training a machine learning model over the incomplete data requires two steps. First, it requires a data-effective step that cleans the data in order to improve the data quality …
View article: EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrieval
EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrieval Open
Misinformation continues to pose a significant challenge in today's information ecosystem, profoundly shaping public perception and behavior. Among its various manifestations, Out-of-Context (OOC) misinformation is particularly obscure, as…
View article: Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering
Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering Open
Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images. Although cutting-edge multimodal large language models (MLLMs) such as GPT-4o achieve strong performance on VQ…
View article: Graph Neural Networks for Databases: A Survey
Graph Neural Networks for Databases: A Survey Open
Graph neural networks (GNNs) are powerful deep learning models for graph-structured data, demonstrating remarkable success across diverse domains. Recently, the database (DB) community has increasingly recognized the potentiality of GNNs, …
View article: Atom of Thoughts for Markov LLM Test-Time Scaling
Atom of Thoughts for Markov LLM Test-Time Scaling Open
Large Language Models (LLMs) achieve superior performance through training-time scaling, and test-time scaling further enhances their capabilities by conducting effective reasoning during inference. However, as the scale of reasoning incre…
View article: AskChart: Universal Chart Understanding through Textual Enhancement
AskChart: Universal Chart Understanding through Textual Enhancement Open
Chart understanding tasks such as ChartQA and Chart-to-Text involve automatically extracting and interpreting key information from charts, enabling users to query or convert visual data into structured formats. State-of-the-art approaches …
View article: SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values
SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values Open
Missing value is a critical issue in data science, significantly impacting the reliability of analyses and predictions. Missing value imputation (MVI) is a longstanding problem because it highly relies on domain knowledge. Large language m…
View article: DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models
DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models Open
The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's V0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their …
View article: AFlow: Automating Agentic Workflow Generation
AFlow: Automating Agentic Workflow Generation Open
Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructin…
View article: Are Large Language Models Good Statisticians?
Are Large Language Models Good Statisticians? Open
Large Language Models (LLMs) have demonstrated impressive capabilities across a range of scientific tasks including mathematics, physics, and chemistry. Despite their successes, the effectiveness of LLMs in handling complex statistical tas…
View article: VisTR: Visualizations as Representations for Time-series Table Reasoning
VisTR: Visualizations as Representations for Time-series Table Reasoning Open
Time-series table reasoning interprets temporal patterns and relationships in data to answer user queries. Despite recent advancements leveraging large language models (LLMs), existing methods often struggle with pattern recognition, conte…
View article: Generative AI for visualization: State of the art and future directions
Generative AI for visualization: State of the art and future directions Open
Generative AI (GenAI) has witnessed remarkable progress in recent years and demonstrated impressive performance in various generation tasks in different domains such as computer vision and computational design. Many researchers have attemp…
View article: ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering
ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering Open
Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large language models (MLLMs) like GPT-4o have shown promise in high-l…
View article: Generative AI for Visualization: State of the Art and Future Directions
Generative AI for Visualization: State of the Art and Future Directions Open
Generative AI (GenAI) has witnessed remarkable progress in recent years and demonstrated impressive performance in various generation tasks in different domains such as computer vision and computational design. Many researchers have attemp…
View article: Navi: Data Analysis System Powered by Natural Language Interaction
Navi: Data Analysis System Powered by Natural Language Interaction Open
PDF HTML XML Export Cite reminder Navi: Data Analysis System Powered by Natural Language Interaction DOI: 10.21655/ijsi.1673-7288.00321 Author: Affiliation: Clc Number: Fund Project: Article | Figures | Metrics | Reference | Related | Cite…
View article: GoodCore: Data-effective and Data-efficient Machine Learning through Coreset Selection over Incomplete Data
GoodCore: Data-effective and Data-efficient Machine Learning through Coreset Selection over Incomplete Data Open
Given a dataset with incomplete data (e.g., missing values), training a machine learning model over the incomplete data requires two steps. First, it requires a data-effective step that cleans the data in order to improve the data quality …
View article: Research on Drainage Rights Allocation Based on Game Combination Weight-Improved Matter-Element Extension Model
Research on Drainage Rights Allocation Based on Game Combination Weight-Improved Matter-Element Extension Model Open
The frequent occurrence of floods poses a serious threat to various aspects such as socio-economic development, ecological stability, and safety of people’s lives and properties. In order to reduce flood losses and improve the overall regi…
View article: GALVIS: Visualization Construction through Example-Powered Declarative Programming
GALVIS: Visualization Construction through Example-Powered Declarative Programming Open
Declarative programmatic approaches are an essential modality for data visualization construction. Despite the powerful customization ability, declarative programming requires users to create charts from scratch, thus building a well-desig…
View article: Sevi: Speech-to-Visualization through Neural Machine Translation
Sevi: Speech-to-Visualization through Neural Machine Translation Open
Data visualization is a powerful tool for understating information through visual cues. However, allowing novices to create visualization artifacts for what they want to see is not easy, just as not everyone can write SQL queries. Arguably…