Hua Wei
YOU?
Author Swipe
View article: cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending Open
View article: A plasmode simulation-based bias analysis for residual confounding by unmeasured variables leveraging information-rich subsets
A plasmode simulation-based bias analysis for residual confounding by unmeasured variables leveraging information-rich subsets Open
Background Quantitative bias analyses often rely on unrealistic assumptions and do not fully reflect the complexities of healthcare data. Methods We describe a ‘plasmode’ simulation-based bias analysis for residual confounding from unmeasu…
View article: Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes
Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes Open
Representational harms in language technologies often occur in short spans within otherwise neutral text, where phrases may simultaneously convey generalizations, unfairness, or stereotypes. Framing bias detection as sentence-level classif…
View article: The relationship between albumin-corrected anion gap and hyperuricemia and its role in cardiovascular risk assessment: mediation effect analysis of triglycerides and non-high-density lipoproteins
The relationship between albumin-corrected anion gap and hyperuricemia and its role in cardiovascular risk assessment: mediation effect analysis of triglycerides and non-high-density lipoproteins Open
Background This study examines the relationship between Albumin-Corrected Anion Gap (ACAG) and hyperuricemia (HUA), as well as its potential mechanisms linking HUA to cardiovascular diseases. While HUA is associated with cardiovascular con…
View article: Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks Open
Explaining Graph Neural Networks (GNNs) has garnered significant attention due to the need for interpretability, enabling users to understand the behavior of these black-box models better and extract valuable insights from their prediction…
View article: 4th Workshop on Uncertainty Reasoning and Quantification in Decision Making (UDM)
4th Workshop on Uncertainty Reasoning and Quantification in Decision Making (UDM) Open
View article: The 4th Workshop on AI Agent for Information Retrieval: Generating and Ranking
The 4th Workshop on AI Agent for Information Retrieval: Generating and Ranking Open
View article: DeepShade: Enable Shade Simulation by Text-conditioned Image Generation
DeepShade: Enable Shade Simulation by Text-conditioned Image Generation Open
Heatwaves pose a significant threat to public health, especially as global warming intensifies. However, current routing systems (e.g., online maps) fail to incorporate shade information due to the difficulty of estimating shades directly …
View article: Multiscale investigation of mechanical anisotropy and machining-induced damage mechanisms in single-crystal gallium Nitride: Insights from first-principles calculations and molecular dynamics simulations
Multiscale investigation of mechanical anisotropy and machining-induced damage mechanisms in single-crystal gallium Nitride: Insights from first-principles calculations and molecular dynamics simulations Open
View article: OP0102 Efficacy and Safety of Xeligekimab in Radiographic Axial Spondyloarthritis: Results from a Phase 3 Trial
OP0102 Efficacy and Safety of Xeligekimab in Radiographic Axial Spondyloarthritis: Results from a Phase 3 Trial Open
View article: GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs
GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs Open
Large Language Models are now key assistants in human decision-making processes. However, a common note always seems to follow: "LLMs can make mistakes. Be careful with important info." This points to the reality that not all outputs from …
View article: Reproducible and Low-cost Sim-to-Real Environment for Traffic Signal Control
Reproducible and Low-cost Sim-to-Real Environment for Traffic Signal Control Open
View article: Uncertainty Quantification for Physics-Informed Traffic Graph Networks
Uncertainty Quantification for Physics-Informed Traffic Graph Networks Open
View article: RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation Open
3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applicatio…
View article: Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey
Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey Open
Large Language Models (LLMs) excel in text generation, reasoning, and decision-making, enabling their adoption in high-stakes domains such as healthcare, law, and transportation. However, their reliability is a major concern, as they often…
View article: A U-shaped non-linear association between serum uric acid levels and the risk of Hashimoto’s thyroiditis: a cross-sectional study
A U-shaped non-linear association between serum uric acid levels and the risk of Hashimoto’s thyroiditis: a cross-sectional study Open
Objective Previous studies have found that the relationship between metabolic indicators and Hashimoto’s thyroiditis (HT) in non-diabetic adults remains unclear. This study aims to explore the association between metabolic indicators and H…
View article: Hypergravity-Assisted Fabrication of Functionally Graded Cu–Ag Alloys with Continuous Microstructural and Compositional Gradients
Hypergravity-Assisted Fabrication of Functionally Graded Cu–Ag Alloys with Continuous Microstructural and Compositional Gradients Open
View article: Microstructure and Dislocation Behavior of Nickel-Based Single Crystal Superalloy Dd6 Under High-Speed Rotation and Complex Stress at 1050 °C
Microstructure and Dislocation Behavior of Nickel-Based Single Crystal Superalloy Dd6 Under High-Speed Rotation and Complex Stress at 1050 °C Open
View article: Atomic-Scale Investigation of Material Damage and Removal Behavior in Ultrasonic Elliptical Vibration-Assisted Cutting of Inp Crystals
Atomic-Scale Investigation of Material Damage and Removal Behavior in Ultrasonic Elliptical Vibration-Assisted Cutting of Inp Crystals Open
View article: CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic
CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic Open
The integration of autonomous vehicles into urban traffic has great potential to improve efficiency by reducing congestion and optimizing traffic flow systematically. In this paper, we introduce CoMAL (Collaborative Multi-Agent LLMs), a fr…
View article: Analysis of the correlation between Hashimoto’s thyroiditis and food intolerance
Analysis of the correlation between Hashimoto’s thyroiditis and food intolerance Open
Objective This study aims to explore the correlation between patients with Hashimoto’s thyroiditis and food intolerance. Methods A total of 172 subjects who visited Guangdong Provincial Hospital of Traditional Chinese Medicine between Janu…
View article: CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control
CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control Open
Effective multi-intersection collaboration is pivotal for reinforcement-learning-based traffic signal control to alleviate congestion. Existing work mainly chooses neighboring intersections as collaborators. However, quite a lot of congest…
View article: MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions
MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions Open
Urban traffic is subject to disruptions that cause extended waiting time and safety issues at signalized intersections. While numerous studies have addressed the issue of intelligent traffic systems in the context of various disturbances, …
View article: The unique influence of 1000 °C high-speed rotation simulated turbine blade working conditions on microstructural degradation of single-crystal superalloy NiAlReRu
The unique influence of 1000 °C high-speed rotation simulated turbine blade working conditions on microstructural degradation of single-crystal superalloy NiAlReRu Open
Turbine blades are mainly subjected to thermal stress and gradient centrifugal stress in operational conditions. The effects of centrifugal stress on the microstructural degradation of single crystal superalloys under a multiaxial stress s…
View article: Shaded Route Planning Using Active Segmentation and Identification of Satellite Images
Shaded Route Planning Using Active Segmentation and Identification of Satellite Images Open
Heatwaves pose significant health risks, particularly due to prolonged exposure to high summer temperatures. Vulnerable groups, especially pedestrians and cyclists on sun-exposed sidewalks, motivate the development of a route planning meth…
View article: Metacognitive AI: Framework and the Case for a Neurosymbolic Approach
Metacognitive AI: Framework and the Case for a Neurosymbolic Approach Open
Metacognition is the concept of reasoning about an agent's own internal processes and was originally introduced in the field of developmental psychology. In this position paper, we examine the concept of applying metacognition to artificia…
View article: Fully Heteroscedastic Count Regression with Deep Double Poisson Networks
Fully Heteroscedastic Count Regression with Deep Double Poisson Networks Open
Neural networks capable of accurate, input-conditional uncertainty representation are essential for real-world AI systems. Deep ensembles of Gaussian networks have proven highly effective for continuous regression due to their ability to f…
View article: MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data Open
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making fo…
View article: HumanLight: Incentivizing ridesharing via human-centric deep reinforcement learning in traffic signal control
HumanLight: Incentivizing ridesharing via human-centric deep reinforcement learning in traffic signal control Open
Single occupancy vehicles are the most attractive transportation alternative for many commuters, leading to increased traffic congestion and air pollution. Advancements in information technologies create opportunities for smart solutions t…
View article: eTraM: Event-based Traffic Monitoring Dataset
eTraM: Event-based Traffic Monitoring Dataset Open
Event cameras, with their high temporal and dynamic range and minimal memory usage, have found applications in various fields. However, their potential in static traffic monitoring remains largely unexplored. To facilitate this exploration…