Shunfu Jin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shunfu Jin has a total of 108 co-authors. Here are the top co-authors by number of shared publications:
Wuyi Yue
Department of Intelligence and Informatics, Konan University, Kobe 658-8501, Japan
29 shared publications- Wuyi Yue
Konan Univ, Dept Intelligence & Informat, Kobe, Hyogo 6588501, Japan
20 shared publications - Yutaka Takahashi
Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan
6 shared publications Haixing Wu
5 shared publications- Dianlong You
Yanshan University
4 shared publications Jingwei Geng
Yanshan University
4 shared publications
Latest Publications
- 14 July 2026
- Published by Springer Nature in Cluster Computing
- Vol. 29 (8) , 491
Game-based burst task offloading analysis for MEC-enabled wireless systems subject to primary-backup redundancy scheme
- 14 July 2026
- Published by Springer Nature in Cluster Computing
- Vol. 29 (8) , 491
Game-based burst task offloading analysis for MEC-enabled wireless systems subject to primary-backup redundancy scheme
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1109-1121
Input Reduction Enhanced LLM-based Program Repair
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1109-1121
Open AccessInput Reduction Enhanced LLM-based Program Repair
- 22 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 310
Cross-modal image fusion via dual attention and Mamba
- 22 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 310
Cross-modal image fusion via dual attention and Mamba
- Top Cited PapersOpen Access
- 21 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (2) , 1-38
MORepair : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning
Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair , we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality patches. We apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.
- 21 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (2) , 1-38
Top Cited PapersOpen AccessMORepair : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning
Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair , we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality patches. We apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.
- 30 July 2025
- Published by Elsevier in Information Sciences
- Vol. 720
Escaping posterior collapse: Enhancing variational autoencoders with vine copulas
- 30 July 2025
- Published by Elsevier in Information Sciences
- Vol. 720
Escaping posterior collapse: Enhancing variational autoencoders with vine copulas
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (11) , 12692-12710
Adaptive Computation Offloading Scheme Based on a Collaborative Architecture With Heterogeneous MEC Nodes: A DRL Approach
Mobile edge computing (MEC) has become an effective paradigm to support computation-intensive applications by providing services in close proximity to user devices (UDs). In MEC networks, computation offloading technology is devoted to balancing system load and prolonging UDs' battery life. However, most existing studies on computation offloading take the impractical assumption of the MEC scenario with homogeneous users, ignoring security requirement from certain users. Moreover, with users mobility and task arrivals correlation, most existing computing offloading approaches suffer from inefficient or suboptimal decision making in practical MEC environments. To tackle these issues, by integrating task arrivals correlation within a time slot and environment dynamics between time slots, we propose an adaptive computation offloading scheme based on a collaborative architecture with heterogeneous MEC nodes. First, considering additional security requirement from very important people (VIP) users, we present a novel collaborative architecture by separating edge/cloud servers into public and private nodes. Then, with the architecture, we develop a dynamic computation offloading (DCO) algorithm to realize adaptive computation offloading scheme in MEC environment with mobile users. Particularly, the algorithm involves three stages. 1) By extending Poisson process into Markovian arrival process (MAP), we construct an MAP-based system model to capture the behavior of time-dependent task arrivals and then analyze the system model to derive the system delay in steady state. 2) For the purpose of minimizing the system delay in each time slot, we formulate a computation offloading problem in MEC environment with mobile users. 3) Under a deep reinforcement learning (DRL) framework, by taking the system delay as environmental feedback, we solve the formulated problem and provide offloading decisions in each time slot. We evaluate the performance of DCO algorithm by comparing it with other benchmark algorithms in various application scenarios. Results demonstrate that the proposed DCO algorithm outperforms the compared algorithms in response performance.
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (11) , 12692-12710
Adaptive Computation Offloading Scheme Based on a Collaborative Architecture With Heterogeneous MEC Nodes: A DRL Approach
Mobile edge computing (MEC) has become an effective paradigm to support computation-intensive applications by providing services in close proximity to user devices (UDs). In MEC networks, computation offloading technology is devoted to balancing system load and prolonging UDs' battery life. However, most existing studies on computation offloading take the impractical assumption of the MEC scenario with homogeneous users, ignoring security requirement from certain users. Moreover, with users mobility and task arrivals correlation, most existing computing offloading approaches suffer from inefficient or suboptimal decision making in practical MEC environments. To tackle these issues, by integrating task arrivals correlation within a time slot and environment dynamics between time slots, we propose an adaptive computation offloading scheme based on a collaborative architecture with heterogeneous MEC nodes. First, considering additional security requirement from very important people (VIP) users, we present a novel collaborative architecture by separating edge/cloud servers into public and private nodes. Then, with the architecture, we develop a dynamic computation offloading (DCO) algorithm to realize adaptive computation offloading scheme in MEC environment with mobile users. Particularly, the algorithm involves three stages. 1) By extending Poisson process into Markovian arrival process (MAP), we construct an MAP-based system model to capture the behavior of time-dependent task arrivals and then analyze the system model to derive the system delay in steady state. 2) For the purpose of minimizing the system delay in each time slot, we formulate a computation offloading problem in MEC environment with mobile users. 3) Under a deep reinforcement learning (DRL) framework, by taking the system delay as environmental feedback, we solve the formulated problem and provide offloading decisions in each time slot. We evaluate the performance of DCO algorithm by comparing it with other benchmark algorithms in various application scenarios. Results demonstrate that the proposed DCO algorithm outperforms the compared algorithms in response performance.
- 2 July 2025
- Published by Elsevier in Pattern Recognition
- Vol. 170
Disentangled representation learning with causal effect transmission in variational autoencoder
- 2 July 2025
- Published by Elsevier in Pattern Recognition
- Vol. 170
Disentangled representation learning with causal effect transmission in variational autoencoder
- 23 June 2025
- Published by Elsevier in Ad Hoc Networks
- Vol. 178
Computation offloading in MEC-assisted vehicular networks with task migration and result feedback
- 23 June 2025
- Published by Elsevier in Ad Hoc Networks
- Vol. 178
Computation offloading in MEC-assisted vehicular networks with task migration and result feedback