Jingyan Jiang
I am an Assistant Professor in the college of big data and Internet at Shenzhen Technology University. Previously, I was a senior researcher at Sangfor SRI Lab, Shenzhen, where I worked on optimizing complex networked systems using optimization techniques and machine learning techniques. Also, I was a Postdoc at Shenzhen International Graduate School, Tsinghua University, and advised by Prof. Shutao Xia. Before that, I did my PhD and bachelor at school of CCST, Jilin University, where I was advised by Prof. Liang Hu I was a visiting PhD at Shenzhen International Graduate School, Tsinghua University during 2017-2020, where advised by Prof. Zhi Wang.
Email / Google Scholar / DBLP
I'm leading the SINX (SecurIty and Network + X) Group, and looking for self-motivated students to work with me at SZTU. Please feel free to drop me an email with your CV.
Email: jiangjingyan@sztu.edu.cn
News
Recent Projects
研究方向概览 / Research Direction Overview
智能多媒体感知与推理实验室（Sinx-Lab: Smart Multimedia Learning and Inference Lab）实验室（与清华大学合作的实验室）招募优秀硕士研究生（研究生不限计算机技术或者大数据专业都可以联系）和高年级本科生。课题介绍可以具体参考如下链接： The Smart Multimedia Learning and Inference Lab (Sinx-Lab), a collaborative lab with Tsinghua University, is recruiting outstanding master's students (students from Computer Technology or Big Data majors are welcome) and senior undergraduate students. For more details about the research topics, please refer to the following link: 模型微调和推理小组 | Notion / Model Fine-tuning and Inference Group
主要研究领域 / Primary Research Fields
主要研究方向为：解决核心问题“如何让预训练模型在面临真实生产环境时，性能更好，资源消耗更低？” The primary research focuses on addressing the key question: "How can pre-trained models perform better and consume fewer resources in real-world production environments?"
- 针对多模态、具身智能和边缘计算场景的深度模型 / LLM 的模型微调与推理部署优化。 Fine-tuning and inference deployment optimization for deep models/LLMs in multimodal, embodied AI, and edge computing scenarios.
这些技术应用场景广泛，包括但不限于：自动驾驶、大模型、工业互联网、具身智能、推广搜索等。 These technologies have wide-ranging applications, including but not limited to autonomous driving, large models, industrial IoT, embodied AI, and search engines.
实验室优势 / Laboratory Advantages
- 计算机主流科研方向与正统培养模式 / Mainstream Research Directions in Computer Science with Rigorous Training：目标投稿计算机专业主流期刊和会议。 Targeting publications in mainstream computer science journals and conferences.
- 丰富津贴 / Generous Financial Support：助教津贴 / 助研津贴 / 论文绩效奖励 / 资助学术会议 / 团建等。 Teaching assistantship, research assistantship, paper performance rewards, academic conference funding, and team-building activities.
- 课题组项目资金充裕 / Well-funded Research Projects：硬件和软件环境优越。 Excellent hardware and software environments.
- 支持多元发展 / Support for Diverse Development：提供推荐实习 / 就业机会，组内氛围愉快。 Offers recommendations for internships and job opportunities, with a friendly and supportive team atmosphere.
Talks
Publications
Conference Papers:
- Cosmic: Clique-oriented semantic multi-space integration for robust clip test-time adaptation.
F. Huang*, J. Jiang*, Q. Jiang, H. Li, F. N. Khan, and Z. Wang
CVPR 2025 | paper (CCF A, co-first author) - Datta: Towards diversity adaptive test-time adaptation in dynamic wild world.
Ye, D. Wei, Z. Liu, Y. Pang, Y. Lin, J. Liao, Q. Jiang, D. He, and J. Jiang †
IEEE ICME 2025 | paper (CCF B, corresponding author, first author from Shenzhen Technology University) - Q-dit: Accurate post-training quantization for diffusion transformers.
L. Chen, Y. Meng, C. Tang, X. Ma, J. Jiang, X. Wang, Z. Wang, and W. Zhu
CVPR 2025 | paper (CCF A) - LLM4Band: Enhancing reinforcement learning with large language models for accurate bandwidth estimation.
Wang, R. Lu, C. Westphal, D. He, and J. Jiang*
NOSSDAV 2025 | paper (CCF B, corresponding author, first author from Shenzhen Technology University) - Joint Model and Data Adaptation for Cloud Inference Serving.
Jingyan Jiang, Ziyue Luo, Chenghao Hu, Zhaoliang He, Zhi Wang, Shutao Xia and Chuan Wu
RTSS 2021 | paper（CCF A） - Decentralized federated learning: A segmented gossip approach
Chenghao Hu, Jingyan Jiang, Zhi Wang
IJCAI Workshop 2019 | paper - Jalad: Joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution
Hongshan Li, Chenghao Hu, Jingyan Jiang, Zhi Wang, Yonggang Wen, Wenwu Zhu
ICPADS 2018 | paper （CCF C）
Journal Papers:
- Fast-DRD: Fast decentralized reinforcement distillation for deadline-aware edge computing
Shinan Song, Zhiyi Fang, Jingyan Jiang*
Information Processing & Management 2022 |paper | * Indicate Corresponding Author. （SCI 1） - Reinforcement learning approach for resource allocation in humanitarian logistics
Lina Yu, Canrong Zhang, Jingyan Jiang, Huasheng Yang, Huayan Shang
Expert Systems with Applications 2021 | paper - Decentralised federated learning with adaptive partial gradient aggregation
Jingyan Jiang, Liang Hu
CAAI Transactions on Intelligence Technology 2020 | paper （JCR Q1） - BACombo—Bandwidth-aware decentralized federated learning
Jingyan Jiang, Liang Hu, Chenghao Hu, Jiate Liu, Zhi Wang
Electronics 2020 | paper - Dynamic pricing with traffic engineering for adaptive video streaming over software-defined content delivery networking
Pingting Hao, Liang Hu, Kuo Zhao, Jingyan Jiang, Tong Li, Xilong Che
Multimedia Tools and Applications 2019 | paper - Q-FDBA: improving QoE fairness for video streaming
Jingyan Jiang, Liang Hu, Pingting Hao, Rui Sun, Jiejun Hu, Hongtu Li
Multimedia Tools and Applications 2018 | paper - Mobile edge provision with flexible deployment
Pingting Hao, Liang Hu, Jingyan Jiang, Jiejun Hu, Xilong Che
IEEE Transactions on Services Computing 2016 | paper （SCI 1） - Environment observation system based on semantics in the internet of things
Liang Hu, Jingyan Jiang, Jin Zhou, Kuo Zhao, Liang Chen, Huimin Lu
Journal of Networks 2013 | paper