Jun Sun
YOU?
Author Swipe
View article: Multi-Length Prediction of the Drilling Rate of Penetration Based on TCN–Informer
Multi-Length Prediction of the Drilling Rate of Penetration Based on TCN–Informer Open
The Rate of Penetration (ROP) during drilling is nonstationary and exhibits coupled local fluctuations, which makes it challenging to model for accurate prediction. To address the challenge of modeling multi-scale temporal dependencies in …
View article: Generalized Security-Preserving Refinement for Concurrent Systems
Generalized Security-Preserving Refinement for Concurrent Systems Open
Ensuring compliance with Information Flow Security (IFS) is known to be challenging, especially for concurrent systems with large codebases such as multicore operating system (OS) kernels. Refinement, which verifies that an implementation …
View article: Correct-by-Construction: Certified Individual Fairness through Neural Network Training
Correct-by-Construction: Certified Individual Fairness through Neural Network Training Open
Fairness in machine learning is more important than ever as ethical concerns continue to grow. Individual fairness demands that individuals differing only in sensitive attributes receive the same outcomes. However, commonly used machine le…
View article: Fuzzing C++ Compilers via Type-Driven Mutation
Fuzzing C++ Compilers via Type-Driven Mutation Open
C++ is a system-level programming language for modern software development, which supports multiple programming paradigms, including object-oriented, generic, and functional programming. The intrinsic complexity of these paradigms and thei…
View article: Development of organoids for drug research and tissue regeneration
Development of organoids for drug research and tissue regeneration Open
View article: Same-group element replacement enhances superconductivity in clathrate-like YH4
Same-group element replacement enhances superconductivity in clathrate-like YH4 Open
H3S, LaH10, and hydrogen-based compounds have garnered significant interest due to their high-temperature superconducting properties. However, the requirement for extremely high pressures limits their practical applications. In this study,…
View article: Oxidative balance and survival in osteoporosis: how antioxidant diets and lifestyles reduce mortality risk
Oxidative balance and survival in osteoporosis: how antioxidant diets and lifestyles reduce mortality risk Open
Background Osteoporosis (OP) is a global health issue characterized by reduced bone mineral density (BMD) and an elevated risk of fractures. Oxidative stress is implicated in OP pathogenesis, and antioxidant diets and lifestyles may mitiga…
View article: FPGA-based hardware implementation of enhanced insulin delivery system: Advancements in biochemical process control for extreme manufacturing applications
FPGA-based hardware implementation of enhanced insulin delivery system: Advancements in biochemical process control for extreme manufacturing applications Open
View article: Enhancing Vulnerability Detection via Inter-procedural Semantic Completion
Enhancing Vulnerability Detection via Inter-procedural Semantic Completion Open
Inspired by advances in deep learning, numerous learning-based approaches for vulnerability detection have emerged, primarily operating at the function level for scalability. However, this design choice has a critical limitation: many vuln…
View article: On-Demand Scenario Generation for Testing Automated Driving Systems
On-Demand Scenario Generation for Testing Automated Driving Systems Open
The safety and reliability of Automated Driving Systems (ADS) are paramount, necessitating rigorous testing methodologies to uncover potential failures before deployment. Traditional testing approaches often prioritize either natural scena…
View article: Meniscus and pressure co-guided printing of liquid metal circuits for soft electronics
Meniscus and pressure co-guided printing of liquid metal circuits for soft electronics Open
View article: A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment Open
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across vario…
View article: Quantitative Runtime Monitoring of Ethereum Transaction Attacks
Quantitative Runtime Monitoring of Ethereum Transaction Attacks Open
View article: Verification of Bit-Flip Attacks against Quantized Neural Networks
Verification of Bit-Flip Attacks against Quantized Neural Networks Open
In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to i…
View article: FPGA implementation of a complete digital spiking silicon neuron for circuit design and network approach
FPGA implementation of a complete digital spiking silicon neuron for circuit design and network approach Open
When attempting to replicate the same biological spiking neuron model actions of the human brain, the spiking neuron model methodology and hardware realization design for the nervous system of the brain are crucial considerations. This wor…
View article: Verification of Bit-Flip Attacks against Quantized Neural Networks
Verification of Bit-Flip Attacks against Quantized Neural Networks Open
In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to i…
View article: PINK: physical-informed machine learning for lattice thermal conductivity
PINK: physical-informed machine learning for lattice thermal conductivity Open
Lattice thermal conductivity (κL ) is crucial for efficient thermal management in electronics and energy conversion technologies. Traditional methods for predicting κL are often computationally expensive, limiting their scalability for larg…
View article: The L-shaped association between body roundness index and all-cause mortality in osteoporotic patients: a cohort study based on NHANES data
The L-shaped association between body roundness index and all-cause mortality in osteoporotic patients: a cohort study based on NHANES data Open
Purpose This study aims to investigate the relationship between the body roundness index (BRI) and overall mortality rates in individuals with osteoporosis (OP), utilizing information sourced from the NHANES database, in order to assess BR…
View article: Space of ancient caloric functions on some manifolds beyond volume doubling
Space of ancient caloric functions on some manifolds beyond volume doubling Open
Under a condition that breaks the volume doubling barrier, we obtain a time polynomial structure result on the space of ancient caloric functions with polynomial growth on manifolds. As a byproduct, it is shown that the finiteness result f…
View article: Automated Program Refinement: Guide and Verify Code Large Language Model with Refinement Calculus
Automated Program Refinement: Guide and Verify Code Large Language Model with Refinement Calculus Open
Recently, the rise of code-centric Large Language Models (LLMs) has reshaped the software engineering world with low-barrier tools like Copilot that can easily generate code. However, there is no correctness guarantee for the code generate…
View article: 西菲律宾海盆东部第四纪沉积物磁学记录及其古气候意义
西菲律宾海盆东部第四纪沉积物磁学记录及其古气候意义 Open
View article: Similarity-Based Prototype Reconstruction and Feature Reorganization for Non-Exemplar Class Incremental Learning
Similarity-Based Prototype Reconstruction and Feature Reorganization for Non-Exemplar Class Incremental Learning Open
View article: Fl-Mhae: Federated-Learning-Based Multiresolution Hybrid Auto-Encoder for Image Classification
Fl-Mhae: Federated-Learning-Based Multiresolution Hybrid Auto-Encoder for Image Classification Open
View article: PonziLens+: Visualizing Bytecode Actions for Smart Ponzi Scheme Identification
PonziLens+: Visualizing Bytecode Actions for Smart Ponzi Scheme Identification Open
With the prevalence of smart contracts, smart Ponzi schemes have become a common fraud on blockchain and have caused significant financial loss to cryptocurrency investors in the past few years. Despite the critical importance of detecting…
View article: ISFM-SLAM: dynamic visual SLAM with instance segmentation and feature matching
ISFM-SLAM: dynamic visual SLAM with instance segmentation and feature matching Open
Introduction Simultaneous Localization and Mapping (SLAM) is a technology used in intelligent systems such as robots and autonomous vehicles. Visual SLAM has become a more popular type of SLAM due to its acceptable cost and good scalabilit…
View article: Efficient low-cost design for high-frequency, accurate hardware implementation of cardiac Purkinje fiber cells for biomedical engineering approaches
Efficient low-cost design for high-frequency, accurate hardware implementation of cardiac Purkinje fiber cells for biomedical engineering approaches Open
Within the heart’s ventricle walls are where Purkinje fibers (PFs) are located. They are essential for maintaining a steady cardiac beat because they allow the heart’s conduction system to create synchronized contractions of its ventricles…
View article: Scoping Software Engineering for AI: The TSE Perspective
Scoping Software Engineering for AI: The TSE Perspective Open
IEEE TSE would like to take a more nuanced approach with respect to reviewing these “SE for AI” papers. Specifically, we observe that submitted manuscripts frequently go into the depths of core AI techniques to improve them in various ways…
View article: UniAdapt: A Universal Adapter for Knowledge Calibration
UniAdapt: A Universal Adapter for Knowledge Calibration Open
Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challenges in balancing ge…
View article: Certified Continual Learning for Neural Network Regression
Certified Continual Learning for Neural Network Regression Open
View article: Certified Quantization Strategy Synthesis for Neural Networks
Certified Quantization Strategy Synthesis for Neural Networks Open
Quantization plays an important role in deploying neural networks on embedded, real-time systems with limited computing and storage resources (e.g., edge devices). It significantly reduces the model storage cost and improves inference effi…