Selected work

Representative Papers

AGMARL-DKS: An Adaptive Graph-Enhanced Multi-Agent Reinforcement Learning for Dynamic Kubernetes Scheduling

Mar 12, 2026

This work proposes a collaborative multi-agent reinforcement learning–based scheduling framework to address the limitations of existing Kubernetes schedulers in large-scale heterogeneous clusters, particularly regarding scalability, dynamic multi-objective optimization, and stress awareness. The approach models each node as an agent and employs a centralized training with decentralized execution paradigm, leveraging graph neural networks to construct a decentralized yet globally informed state representation. A stress-aware lexicographic policy is designed to dynamically prioritize and balance competing objectives. Experimental evaluation on Google Kubernetes Engine demonstrates that the proposed scheduler significantly outperforms the default Kubernetes scheduler, achieving superior resource utilization, fault tolerance, and cost efficiency—especially under mixed workloads comprising both batch and latency-sensitive critical tasks.

0 citationsRead paper

CoGen: Creation of Reusable UI Components in Figma via Textual Commands

Jan 15, 2026

This work addresses the limitation of current UI design tools in efficiently generating reusable and editable atomic components from natural language. The authors propose an end-to-end approach that, for the first time, integrates a fine-tuned T5 model with the Figma API to automatically produce editable UI atomic components—such as buttons and input fields—from natural language instructions via structured JSON representations and textual prompts. Leveraging a sequence-to-sequence architecture, the method achieves 98% accuracy and a BLEU score of 0.2668 on prompt generation tasks. Notably, for specified component types, the system attains a 100% success rate in generating valid simple JSON structures, substantially advancing the automation of UI design and enhancing component reusability.

0 citationsRead paper

SHERLOCK: A Deep Learning Approach To Detect Software Vulnerabilities

Dec 14, 2025

Traditional static and dynamic analysis tools suffer from low accuracy and poor generalizability in detecting diverse software vulnerabilities. To address this, this paper proposes an end-to-end, function-level vulnerability detection method based on Convolutional Neural Networks (CNNs). The approach takes lexically tokenized source code as input and is the first to systematically apply CNNs to fine-grained, multi-class vulnerability identification—covering critical CWE types including CWE-199 and CWE-120. Evaluated via lexical tokenization and five-fold cross-validation across multiple benchmark datasets, the method achieves high classification accuracy, with significantly improved true positive and true negative rates over state-of-the-art static and dynamic analyzers. Key contributions include: (1) the first CNN-based framework tailored for function-level, multi-CWE vulnerability detection; (2) empirical validation of lexical sequence modeling efficacy for vulnerability detection; and (3) substantial performance gains in identifying critical security defects.

0 citationsRead paper

Workload Schedulers -- Genesis, Algorithms and Differences

Nov 13, 2025

This paper addresses the lack of clarity regarding the diversity and evolutionary trajectories of modern workload schedulers. We propose a cross-layer taxonomy comprising three categories: OS process scheduling, cluster job scheduling, and big-data scheduling. Through algorithmic feature analysis and historical comparative study, we systematically characterize the design rationales, optimization objectives, and technological evolution of these schedulers, uncovering shared design patterns across local and distributed environments. Our key contribution is the first unified classification framework, which identifies three fundamental differentiating dimensions: resource abstraction granularity, scheduling timing, and feedback mechanism. Based on this analysis, we distill general-purpose scheduling design principles targeting heterogeneity, scalability, and QoS guarantees. The study provides both theoretical foundations and practical guidance for scheduler selection, cross-layer coordination optimization, and next-generation scheduler architecture design.

0 citationsRead paper

A Meta-Heuristic Load Balancer for Cloud Computing Systems

Nov 12, 2025

To address service load balancing under multiple resource constraints in cloud environments, this paper proposes an enhanced genetic algorithm integrating high-quality solutions from diverse metaheuristics (e.g., PSO, SA) as the initial population—thereby accelerating convergence and improving solution quality. The method incorporates abstracted resource modeling, fine-grained multi-dimensional load evaluation, and an explicit service migration overhead quantification model to enable cost-aware dynamic scheduling. Experiments on heterogeneous cloud platforms demonstrate that the proposed algorithm reduces average node load by 23.6%, decreases service migration count by 31.4%, and lowers total operational cost by 18.9%, while maintaining system stability and SLA compliance. The core contributions are: (1) a multi-objective optimization framework with explicit migration cost modeling, and (2) empirical validation that multi-strategy initialization significantly enhances the effectiveness of genetic algorithms for cloud workload scheduling.

0 citationsRead paper

Recent publications

Latest Papers

AGMARL-DKS: An Adaptive Graph-Enhanced Multi-Agent Reinforcement Learning for Dynamic Kubernetes Scheduling

Mar 12, 2026

This work proposes a collaborative multi-agent reinforcement learning–based scheduling framework to address the limitations of existing Kubernetes schedulers in large-scale heterogeneous clusters, particularly regarding scalability, dynamic multi-objective optimization, and stress awareness. The approach models each node as an agent and employs a centralized training with decentralized execution paradigm, leveraging graph neural networks to construct a decentralized yet globally informed state representation. A stress-aware lexicographic policy is designed to dynamically prioritize and balance competing objectives. Experimental evaluation on Google Kubernetes Engine demonstrates that the proposed scheduler significantly outperforms the default Kubernetes scheduler, achieving superior resource utilization, fault tolerance, and cost efficiency—especially under mixed workloads comprising both batch and latency-sensitive critical tasks.

0 citationsRead paper

CoGen: Creation of Reusable UI Components in Figma via Textual Commands

Jan 15, 2026

This work addresses the limitation of current UI design tools in efficiently generating reusable and editable atomic components from natural language. The authors propose an end-to-end approach that, for the first time, integrates a fine-tuned T5 model with the Figma API to automatically produce editable UI atomic components—such as buttons and input fields—from natural language instructions via structured JSON representations and textual prompts. Leveraging a sequence-to-sequence architecture, the method achieves 98% accuracy and a BLEU score of 0.2668 on prompt generation tasks. Notably, for specified component types, the system attains a 100% success rate in generating valid simple JSON structures, substantially advancing the automation of UI design and enhancing component reusability.

0 citationsRead paper

SHERLOCK: A Deep Learning Approach To Detect Software Vulnerabilities

Dec 14, 2025

Traditional static and dynamic analysis tools suffer from low accuracy and poor generalizability in detecting diverse software vulnerabilities. To address this, this paper proposes an end-to-end, function-level vulnerability detection method based on Convolutional Neural Networks (CNNs). The approach takes lexically tokenized source code as input and is the first to systematically apply CNNs to fine-grained, multi-class vulnerability identification—covering critical CWE types including CWE-199 and CWE-120. Evaluated via lexical tokenization and five-fold cross-validation across multiple benchmark datasets, the method achieves high classification accuracy, with significantly improved true positive and true negative rates over state-of-the-art static and dynamic analyzers. Key contributions include: (1) the first CNN-based framework tailored for function-level, multi-CWE vulnerability detection; (2) empirical validation of lexical sequence modeling efficacy for vulnerability detection; and (3) substantial performance gains in identifying critical security defects.

0 citationsRead paper

Workload Schedulers -- Genesis, Algorithms and Differences

Nov 13, 2025

This paper addresses the lack of clarity regarding the diversity and evolutionary trajectories of modern workload schedulers. We propose a cross-layer taxonomy comprising three categories: OS process scheduling, cluster job scheduling, and big-data scheduling. Through algorithmic feature analysis and historical comparative study, we systematically characterize the design rationales, optimization objectives, and technological evolution of these schedulers, uncovering shared design patterns across local and distributed environments. Our key contribution is the first unified classification framework, which identifies three fundamental differentiating dimensions: resource abstraction granularity, scheduling timing, and feedback mechanism. Based on this analysis, we distill general-purpose scheduling design principles targeting heterogeneity, scalability, and QoS guarantees. The study provides both theoretical foundations and practical guidance for scheduler selection, cross-layer coordination optimization, and next-generation scheduler architecture design.

0 citationsRead paper

A Meta-Heuristic Load Balancer for Cloud Computing Systems

Nov 12, 2025

To address service load balancing under multiple resource constraints in cloud environments, this paper proposes an enhanced genetic algorithm integrating high-quality solutions from diverse metaheuristics (e.g., PSO, SA) as the initial population—thereby accelerating convergence and improving solution quality. The method incorporates abstracted resource modeling, fine-grained multi-dimensional load evaluation, and an explicit service migration overhead quantification model to enable cost-aware dynamic scheduling. Experiments on heterogeneous cloud platforms demonstrate that the proposed algorithm reduces average node load by 23.6%, decreases service migration count by 31.4%, and lowers total operational cost by 18.9%, while maintaining system stability and SLA compliance. The core contributions are: (1) a multi-objective optimization framework with explicit migration cost modeling, and (2) empirical validation that multi-strategy initialization significantly enhances the effectiveness of genetic algorithms for cloud workload scheduling.

0 citationsRead paper