Ze Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ze Yang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Yihong Jin
University of Illinois at Urbana-Champaign, USA
5 shared publications - Xinhe Xu
University of Illinois Urbana-Champaign Champaign USA
4 shared publications Juntian Liu
3 shared publications- Yihan Zhang2 shared publications
- ChiaHua Chang
Boston University, USA
1 shared publication - Haoran Zheng
University of Pennsylvania, USA
1 shared publication
Latest Publications
- Open Access
- 30 June 2025
- Published by MDPI AG in Preprints.org
FinGPT-Agent: An Advanced Framework for Multimodal Research Report Generation with Task-Adaptive Optimization and Hierarchical Attention
Financial research report generation is challengingdue to diverse data types, real-time requirements, and thecomplexity of financial analysis. This paper introduces FinGPT-Agent, a multi-agent framework that uses Large LanguageModels (LLMs) to tackle these challenges. The frameworkincludes multimodal fusion for handling different data types,task-specific optimization with Low-Rank Adaptation (LoRA),retrieval-augmented generation with contrastive learning forbetter context, and reinforcement learning with human feedbackto improve report quality. A hierarchical attention mechanismhelps summarize long financial documents. Experiments showthat FinGPT-Agent performs better than baseline models andsets a benchmark for financial report generation using LLMs.
- 30 June 2025
- Published by MDPI AG in Preprints.org
Open AccessFinGPT-Agent: An Advanced Framework for Multimodal Research Report Generation with Task-Adaptive Optimization and Hierarchical Attention
Financial research report generation is challengingdue to diverse data types, real-time requirements, and thecomplexity of financial analysis. This paper introduces FinGPT-Agent, a multi-agent framework that uses Large LanguageModels (LLMs) to tackle these challenges. The frameworkincludes multimodal fusion for handling different data types,task-specific optimization with Low-Rank Adaptation (LoRA),retrieval-augmented generation with contrastive learning forbetter context, and reinforcement learning with human feedbackto improve report quality. A hierarchical attention mechanismhelps summarize long financial documents. Experiments showthat FinGPT-Agent performs better than baseline models andsets a benchmark for financial report generation using LLMs.
- Open Access
- 11 June 2025
- Published by MDPI AG in Preprints.org
Adversarial Prompt Optimization in LLMs: HijackNet's Approach to Robustness and Defense Evasion
This paper introduces HijackNet, an adversarial prompt hijacking framework designed to improve hijacking success rates and generalization in multi-lingual tasks. Combining Neural Architecture Search (NAS), Reinforcement Learning (RL), and Multi-Objective Optimization (MOO), HijackNet generates adversarial prompts that adapt to target tasks while bypassing model defense mechanisms. This framework optimizes hijacking success, defense evasion, and task completion through a combination of a prompt generator and adversarial optimizer. We introduce a Defense Robustness Score (DRS) to evaluate the stability of prompts in adversarial settings. HijackNet improves adversarial prompt generation, advancing the security and robustness of large language models in adversarial environments.
- 11 June 2025
- Published by MDPI AG in Preprints.org
Open AccessAdversarial Prompt Optimization in LLMs: HijackNet's Approach to Robustness and Defense Evasion
This paper introduces HijackNet, an adversarial prompt hijacking framework designed to improve hijacking success rates and generalization in multi-lingual tasks. Combining Neural Architecture Search (NAS), Reinforcement Learning (RL), and Multi-Objective Optimization (MOO), HijackNet generates adversarial prompts that adapt to target tasks while bypassing model defense mechanisms. This framework optimizes hijacking success, defense evasion, and task completion through a combination of a prompt generator and adversarial optimizer. We introduce a Defense Robustness Score (DRS) to evaluate the stability of prompts in adversarial settings. HijackNet improves adversarial prompt generation, advancing the security and robustness of large language models in adversarial environments.
- Open Access
An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning
As the scale and complexity of cloud-based AI systems continue to increase, the detection and adaptive recovery of system faults have become the core challenges to ensure service reliability and continuity. In this paper, we propose an Intelligent Fault Self-Healing Mechanism (IFSHM) that integrates Large Language Model (LLM) and Deep Reinforcement Learning (DRL), aiming to realize a fault recovery framework with semantic understanding and policy optimization capabilities in cloud AI systems. On the basis of the traditional DRL-based control model, the proposed method constructs a two-stage hybrid architecture: (1) an LLM-driven fault semantic interpretation module, which can dynamically extract deep contextual semantics from multi-source logs and system indicators to accurately identify potential fault modes; (2) DRL recovery strategy optimizer, based on reinforcement learning, learns the dynamic matching of fault types and response behaviors in the cloud environment. The innovation of this method lies in the introduction of LLM for environment modeling and action space abstraction, which greatly improves the exploration efficiency and generalization ability of reinforcement learning. At the same time, a memory-guided meta-controller is introduced, combined with reinforcement learning playback and LLM prompt fine-tuning strategy, to achieve continuous adaptation to new failure modes and avoid catastrophic forgetting. Experimental results on the cloud fault injection platform show that compared with the existing DRL and rule methods, the IFSHM framework shortens the system recovery time by 37% with unknown fault scenarios.
Open AccessAn Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning
As the scale and complexity of cloud-based AI systems continue to increase, the detection and adaptive recovery of system faults have become the core challenges to ensure service reliability and continuity. In this paper, we propose an Intelligent Fault Self-Healing Mechanism (IFSHM) that integrates Large Language Model (LLM) and Deep Reinforcement Learning (DRL), aiming to realize a fault recovery framework with semantic understanding and policy optimization capabilities in cloud AI systems. On the basis of the traditional DRL-based control model, the proposed method constructs a two-stage hybrid architecture: (1) an LLM-driven fault semantic interpretation module, which can dynamically extract deep contextual semantics from multi-source logs and system indicators to accurately identify potential fault modes; (2) DRL recovery strategy optimizer, based on reinforcement learning, learns the dynamic matching of fault types and response behaviors in the cloud environment. The innovation of this method lies in the introduction of LLM for environment modeling and action space abstraction, which greatly improves the exploration efficiency and generalization ability of reinforcement learning. At the same time, a memory-guided meta-controller is introduced, combined with reinforcement learning playback and LLM prompt fine-tuning strategy, to achieve continuous adaptation to new failure modes and avoid catastrophic forgetting. Experimental results on the cloud fault injection platform show that compared with the existing DRL and rule methods, the IFSHM framework shortens the system recovery time by 37% with unknown fault scenarios.
- Open Access
Anomaly Detection and Early Warning Mechanism for Intelligent Monitoring Systems in Multi-Cloud Environments Based on LLM
With the rapid development of multi-cloud environments, it is increasingly important to ensure the security and reliability of intelligent monitoring systems. In this paper, we propose an anomaly detection and early warning mechanism for intelligent monitoring system in multi-cloud environment based on Large-Scale Language Model (LLM). On the basis of the existing monitoring framework, the proposed model innovatively introduces a multi-level feature extraction method, which combines the natural language processing ability of LLM with traditional machine learning methods to enhance the accuracy of anomaly detection and improve the real-time response efficiency. By introducing the contextual understanding capabilities of LLMs, the model dynamically adapts to different cloud service providers and environments, so as to more effectively detect abnormal patterns and predict potential failures. Experimental results show that the proposed model is significantly better than the traditional anomaly detection system in terms of detection accuracy and latency, and significantly improves the resilience and active management ability of cloud infrastructure.
Open AccessAnomaly Detection and Early Warning Mechanism for Intelligent Monitoring Systems in Multi-Cloud Environments Based on LLM
With the rapid development of multi-cloud environments, it is increasingly important to ensure the security and reliability of intelligent monitoring systems. In this paper, we propose an anomaly detection and early warning mechanism for intelligent monitoring system in multi-cloud environment based on Large-Scale Language Model (LLM). On the basis of the existing monitoring framework, the proposed model innovatively introduces a multi-level feature extraction method, which combines the natural language processing ability of LLM with traditional machine learning methods to enhance the accuracy of anomaly detection and improve the real-time response efficiency. By introducing the contextual understanding capabilities of LLMs, the model dynamically adapts to different cloud service providers and environments, so as to more effectively detect abnormal patterns and predict potential failures. Experimental results show that the proposed model is significantly better than the traditional anomaly detection system in terms of detection accuracy and latency, and significantly improves the resilience and active management ability of cloud infrastructure.
- Open Access
Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environments
With the rapid evolution of Large Language Models (LLMs) and their large-scale experimentation in cloud-computing spaces, the challenge of guaranteeing their security and efficiency in a failure scenario has become a main issue. To ensure the reliability and availability of large-scale language models in cloud computing scenarios, such as frequent resource failures, network problems, and computational overheads, this study proposes a novel adaptive fault tolerance mechanism. It builds upon known fault-tolerant mechanisms, such as checkpointing, redundancy, and state transposition, introducing dynamic resource allocation and prediction of failure based on real-time performance metrics. The hybrid model integrates data driven deep learning-based anomaly detection technique underlining the contribution of cloud orchestration middleware for predictive prevention of system failures. Additionally, the model integrates adaptive checkpointing and recovery strategies that dynamically adapt according to load and system state to minimize the influence on the performance of the model and minimize downtime. The experimental results demonstrate that the designed model considerably enhances the fault tolerance in large-scale cloud surroundings, and decreases the system downtime by $\mathbf{30\%}$, and has a better modeling availability than the classical fault tolerance mechanism.Open AccessAdaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environments
With the rapid evolution of Large Language Models (LLMs) and their large-scale experimentation in cloud-computing spaces, the challenge of guaranteeing their security and efficiency in a failure scenario has become a main issue. To ensure the reliability and availability of large-scale language models in cloud computing scenarios, such as frequent resource failures, network problems, and computational overheads, this study proposes a novel adaptive fault tolerance mechanism. It builds upon known fault-tolerant mechanisms, such as checkpointing, redundancy, and state transposition, introducing dynamic resource allocation and prediction of failure based on real-time performance metrics. The hybrid model integrates data driven deep learning-based anomaly detection technique underlining the contribution of cloud orchestration middleware for predictive prevention of system failures. Additionally, the model integrates adaptive checkpointing and recovery strategies that dynamically adapt according to load and system state to minimize the influence on the performance of the model and minimize downtime. The experimental results demonstrate that the designed model considerably enhances the fault tolerance in large-scale cloud surroundings, and decreases the system downtime by $\mathbf{30\%}$, and has a better modeling availability than the classical fault tolerance mechanism. - Open Access
Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning
The fast development of large language models (LLMs) and popularization of cloud computing have led to increasing concerns on privacy safeguarding and data security of cross-cloud model deployment and training as the key challenges. We present a new framework for addressing these issues along with enabling privacy preserving collaboration on training between distributed clouds based on federated learning. Our mechanism encompasses cutting-edge cryptographic primitives, dynamic model aggregation techniques, and cross-cloud data harmonization solutions to enhance security, efficiency, and scalability to the traditional federated learning paradigm. Furthermore, we proposed a hybrid aggregation scheme to mitigate the threat of Data Leakage and to optimize the aggregation of model updates, thus achieving substantial enhancement on the model effectiveness and stability. Experimental results demonstrate that the training efficiency, privacy protection, and model accuracy of the proposed model compare favorably to those of the traditional federated learning method.
Open AccessResearch on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning
The fast development of large language models (LLMs) and popularization of cloud computing have led to increasing concerns on privacy safeguarding and data security of cross-cloud model deployment and training as the key challenges. We present a new framework for addressing these issues along with enabling privacy preserving collaboration on training between distributed clouds based on federated learning. Our mechanism encompasses cutting-edge cryptographic primitives, dynamic model aggregation techniques, and cross-cloud data harmonization solutions to enhance security, efficiency, and scalability to the traditional federated learning paradigm. Furthermore, we proposed a hybrid aggregation scheme to mitigate the threat of Data Leakage and to optimize the aggregation of model updates, thus achieving substantial enhancement on the model effectiveness and stability. Experimental results demonstrate that the training efficiency, privacy protection, and model accuracy of the proposed model compare favorably to those of the traditional federated learning method.