康海东，甘肃天水人，2025年10月博士毕业于东北大学，同年于12月加入东北大学计算机学院，担任副教授，硕士研究生导师。目前研究方向包括边缘计算，机器学习，协作学习和可信人工智能。在IEEE Transactions on Computers，IEEE Transactions on Mobile Computing，SCIS，ICML2025，ICCV2025，NeurIPS-2025，ACM MM2025，IJCAI2025，AAAI2026，IEEE TNNLS等Top-tier/CCF A顶级期刊/会议发表论文10余篇，中科院1区2篇，SCI 1区1篇，在IJCNN, ICANN等清华B类论文/CCF C论文3篇。一篇CCF A类期刊论文被检索为SCI高被引。授权专利2篇。常年担任TPAMI, TIP，NeurIPS，ICML，ICCV，CVPR，IJCAI，ICLR，AAAI，ACM MM，KDD，TNNLS等高水平期刊/会议的程序委员会委员。在科研项目方面，主持东北大学科研启动资金一项；作为核心成员参与了多个横向/纵向的项目研发。

个人主页：https://www.kdocs.cn/l/co3qrp9EPqnB(实时更新)

联系方式：hdkang@stumail.neu.edu.cn或kanghaidong@qhd.neu.edu.cn或hdkustl@gmail.com

部分代表性成果

1. Kang, Haidong*, Lihong Lin, Hanling Wang. Revolutionizing Training-Free NAS: Towards Efficient Automatic Proxy Discovery via Large Language Models. The Thirty-ninth Annual Conference on Neural Information Processing Systems 2025.(CCF A)

2. Haidong Kang,Ma, Lianbo*, Pengjun Chen, Guo Yu, Qing Li. Beyond the Limits: Overcoming Negative Correlations of Activation-Based Training-Free NAS, International Conference on Computer Vision (ICCV), Oct 19, 2025 - Oct 25, 2025, Honolulu, Hawaii.(CCF A)

3. Haidong Kang*. Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective. The Forty-second International Conference on Machine Learning (ICML2025), July 13-19, 2025, Vancouver, Canada.(CCF A)

4. Haidong Kang,Lianbo Ma*, Pengjun Chen, Qiang He,Bo Yi. Understanding and Enhancing Differentiable Architecture Search From Information Bottleneck Perspective，AAAI 2026(CCF A)

5. Haidong Kang, Ma, Lianbo*, Guo Yu, Shangce Gao. Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization. The 34th International Joint Conference on Artificial Intelligence (IJCAI-25), August 16 to August 22, 2025, Montreal, Canada.(CCF A)

6. Lianbo Ma,Haidong Kang, Guo Yu, Qing Li, Qiang He, Single-Domain Generalized Predictor for Neural Architecture Search System, IEEE Transactions on Computers, 2024. (CCF A，ESI高被引)

7. Hanling Wang, Qing Li*, Li Chen,Haidong Kang, Fei Ma, Yong Jiang. HoloTrace: LLM-based Bidirectional Causal Knowledge Graph for Edge-Cloud Video Anomaly Detection. ACM Multimedia 2025.(CCF A)

8. HL Wang, Q Li*,H Kang, etc. ParaLoupe: Real-time Video Analytics on Edge Cluster via Mini Model Parallelization, IEEE Transactions on Mobile Computing.(CCF A)

9. Jian Cheng,Kang, Haidong, Yuxin Shao, Pengjun Chen, Nan Li, Rui Wang, Saiqin Long, Xiaochun Yang, Lianbo Ma. Survey on Large Language Model Inference Acceleration: Principles, Algorithms, Applications and Open Issues. IEEE TNNLS. (中科院1区TOP,共一)

招生信息：课题组常年招收硕士研究生、本科生和校外实习生（具体见个人主页）。基本要求：热爱人工智能，有自驱力，情绪稳定。本课题组与新加坡南洋理工大学、香港科技大学、香港浸会大学、日本国立富山大学、四川大学、西电等高校保持良好合作关系。课题组多名本科生和实习生发表1-3篇CCF A类论文，并顺利推免至南开大学、浙江大学等高校继续深造。