搜索 
英文 
联系我们 
首页 
个人简介
邵嘉伟：教授，博士生导师
人才称号：国家级青年人才
研究方向：多模态大模型、边缘智能
联系地址：陕西省西安市碑林区友谊西路127号西北工业大学64信箱
邮政编码：710072
电子邮箱：jiawei.shao@nwpu.edu.cn
聚焦人工智能与边缘计算的前沿交叉研究，致力于推动大模型智能能力从云端向资源受限的用户终端下沉，构建响应更实时、隐私更安全、部署更灵活的智能服务体系。研究重点围绕端侧算力不足、边缘频谱资源受限、推理过程隐私泄露等核心问题，面向监控设备、具身机器人、无人机、智能手机等典型终端场景。细分方向包括但不限于端云大小模型协同与推理加速、基于生成模型的数据压缩、推理时隐私保护等。
招生招聘
团队招收硕博士研究生、本科生开展研究工作（目前有多个2026年9月推免名额）。请联系jiawei.shao@nwpu.edu.cn获取更多信息，并附上个人简历、成绩单。
欢迎海外英才依托申报各类人才项目，请联系jiawei.shao@nwpu.edu.cn获取更多信息。
团队招聘博士后，请联系jiawei.shao@nwpu.edu.cn获取更多信息，并附上个人简历、代表性工作。
团队与中国电信股份有限公司人工智能研究院（TeleAI）保持长期合作关系，开展智传网（AI Flow）、生成式智能传输、多模态大模型等方向的研究工作。TeleAI研究院院长为李学龙教授（中国电信CTO、首席科学家）。优秀的本科生、研究生可推荐到TeleAI实习工作，请将简历发送至shaojw2@chinatelecom.cn。[招聘信息]
中国电信股份有限公司人工智能研究院依托工程硕博士培养改革专项，与清华大学、复旦大学、上海交通大学、浙江大学合作，招收企业联合培养工程硕博士。2027级联培招生已经启动，具有推免资格的大三学生可发送简历、成绩单至shaojw2@chinatelecom.cn进行报名。[招生信息]
团队与香港科技大学、香港大学等海外知名高校保持长期密切合作关系，可推荐研究生海外交流。
教育背景
| 2019-2024 | 香港科技大学 | 电子与计算机工程 | 博士 |
| 2015-2019 | 北京邮电大学 | 通信工程 | 学士 |
工作经历
| 2026-至今 | 西北工业大学 | 教授 |
| 2024-2026 | 中国电信股份有限公司人工智能研究院（上海） | 研究科学家 |
近期工作
C. Yuan, Z. Liu, J. Lv, J. Shao, Y. Jiang, J. Zhang, and X. Li, "Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference," IEEE Transactions on Mobile Computing, vol. 25, no. 4, pp. 4762-4775, 2026. [CCF-A类期刊]
C. Chen, J. Shao, D. Lu, H. Hu, X. Liu, H. Yao, and W. Liu, "GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents," Proceedings of the AAAI Conference on Artificial Intelligence, Singapore, 2026. [CCF-A类论文]
Y. Tan, J. Shao, E. Zamfir, R. Li, Z. An, C. Ma, D. Paudel, L. Gool, R. Timofte, and Z. Wu, "What You Have is What You Track: Adaptive and Robust Multimodal Tracking," Proceedings of the IEEE/CVF International Conference on Computer Vision, Honolulu, HI, USA, 2025. [CCF-A类会议]
T. Zhu, S. Zhang, J. Shao, and Y. Tang, "KV-Edit: Training-Free Image Editing for Precise Background Preservation," International Conference on Computer Vision, Honolulu, HI, USA, 2025. [CCF-A类会议]
W. Huang, J. Liang, G. Wan, D. Zhu, H. Li, J. Shao, M. Ye, B. Du, and D. Tao, "Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning," Proceedings of the International Conference on Machine Learning, Vancouver, BC, Canada, 2025. [CCF-A类会议]
H. Li, J. Shao, H. He, S. Song, J. Zhang, and K. B. Letaief, "Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck," IEEE Journal on Selected Areas in Communications, vol. 43, no. 7, pp. 2667-2683, 2025. [SCI 1区，Top期刊]
J. Shao, and X. Li, "AI Flow at the Network Edge," IEEE Network, vol. 40, no. 1, pp. 330-336, 2025.
代表工作
J. Shao, F. Wu, and J. Zhang, “Selective Knowledge Sharing for Privacy-Preserving Federated Distillation Without a Good Teacher,” Nature Communications, vol. 15, no. 1, pp. 349-359, 2024. [Nature 子刊]
J. Shao, X. Zhang, and J. Zhang, “Task-Oriented Communication for Edge Video Analytics,” IEEE Transactions on Wireless Communications, vol. 23, no. 5, pp. 4141-4154, 2024. [SCI 1区，Top期刊]
J. Shao, Y. Mao, and J. Zhang, “Task-Oriented Communication for Multi-Device Cooperative Edge Inference,” IEEE Transactions on Wireless Communications, vol. 22, no. 1, pp. 73-87, 2023. [SCI 1区，Top期刊，ESI高被引论文]
J. Shao, Y. Mao, and J. Zhang, “Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach,” IEEE Journal on Selected Areas in Communications, vol. 40, no. 1, pp. 197-211, 2022. [SCI 1区，Top期刊，ESI高被引论文]
J. Shao, Y. Sun, S. Li, and J. Zhang, “DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing,” Advances in Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, 2022. [CCF-A类会议]
Y. Xie, J. Yi, J. Shao, J. Curl, L. Lyu, Q. Chen, X. Xie, and F. Wu, “Defending ChatGPT against Jailbreak Attack via Self-Reminder,” Nature Machine Intelligence, vol. 5, no. 12, pp. 1486-1496, 2023. [Nature 子刊]
荣誉获奖
学术活动
IEEE GLOBECOM组织“AI Flow: Towards Ubiquitous Intelligence in the Era of Large Foundation Models”主题研讨会。[研讨会主页]
全球云网宽带产业协会宽带发展大会上做“AI Flow - Towards Connected Intelligence via Networked Familial Models”主题报告。
IEEE香港6G无线峰会上做“EdgeGPT: GPT-Empowered Autonomous Edge Inference”主题展示。
期刊审稿人：IEEE Journal on Selected Areas in Communications (JSAC)、IEEE Transactions on Wireless Communications (TWC)、IEEE Transactions on Mobile Computing (TMC)。
会议审稿人：International Conference on Machine Learning (ICML)、International Conference on Learning Representations (ICLR)、Conference on Neural Information Processing Systems (NeurIPS)、Association for the Advancement of Artificial Intelligence Conference (AAAI)、IEEE Global Communications Conference (GLOBECOM)、IEEE International Conference on Communications (ICC)。