Assist. Prof. Dr. Jinyang Guo | Artificial Intelligence | Best Researcher Award
Assist. Prof. Dr. Jinyang Guo, Beihang University, China.
Dr. Jinyang Guo is an Assistant Professor at Beihang University, China, specializing in efficient AI computing π₯οΈ. A recipient of Chinaβs prestigious National Youth Talent Program π¨π³, he has published 40+ papers in top-tier venues like ICML and CVPR π. . His research excellence is complemented by patents, IEEE awards π , and active roles in global AI conferences π.
Profile
π Early Academic Pursuits
Dr. Jinyang Guo began his academic journey in Australia, earning a Bachelor of Engineering (Honors) in Electrical Engineering from The University of New South Wales with First Class Honours and placement on the Deanβs Award List (top 5%) from 2014 to 2017. He pursued a Ph.D. in Electrical and Information Engineering at The University of Sydney, focusing on efficient and scalable machine learning, where he was supported by prestigious scholarships including the USydIS and ARC-backed fellowships.
πΌ Professional Endeavors
Currently serving as an Assistant Professor at the School of Artificial Intelligence, Beihang University, China, Dr. Guo specializes in efficient AI computing. He has emerged as a lead researcher in several national and industrial projects, overseeing more than 10 competitive grants and spearheading initiatives in AI deployment for UAVs, model compression, and human-machine hybrid systems. He also plays active roles in international academic circles through workshops, guest editorships, and conference organizations.
π¬ Contributions and Research Focus On Artificial Intelligence
Dr. Guoβs research focuses on model compression, AI efficiency, sparsity, and scalable learning, addressing real-world challenges in deploying AI on edge and embedded systems. His pioneering work includes multidimensional pruning frameworks, 3D action recognition, and language model compression, bridging fundamental AI theory with impactful applications. His contributions also span human-machine alignment, video diffusion, and efficient large language models.
π Impact and Influence
With over 40 high-impact publications in IEEE Transactions and elite venues such as ICML, CVPR, AAAI, and NeurIPS, Dr. Guo has gained global recognition in AI and machine learning. His research has influenced both academic and industrial practices, contributing significantly to robust model design and resource-constrained AI deployment. His awards include the ICCV Doctoral Consortium Award and 2nd Place in the IEEE Autonomous UAV Challenge 2023, affirming his standing as a rising leader in the field.
π§ Research Skills
Dr. Guo possesses robust skills in model pruning, quantization, and neural network optimization. He is adept at developing scalable solutions for real-world AI applications, such as UAVs and embedded systems. His expertise also spans human-machine alignment, point cloud processing, and transformer-based 3D object detection.
π Awards and Honors
He is a recipient of the ICCV Doctoral Consortium Award, 2nd Place in the 2023 IEEE Autonomous UAV Chase Challenge, and multiple prestigious scholarships, including the University of Sydney International Scholarship, Postgraduate Research Supplementary Scholarship, and Engineering and IT Research Scholarship, amounting to over $147,000 USD in academic suppo
ποΈ Legacy and Future Contributions
Dr. Guo is poised to shape the next generation of AI systems through his innovative work on efficient computing under limited resources. His active involvement in IEEE standardization (e.g., IEEE P3342) and editorial leadership in Q1 journals ensures his influence on global AI standards and discourse. He continues to mentor young researchers and collaborate on cutting-edge projects that integrate AI with human-centric applications, setting the stage for transformative AI technologies in academia and industry.
Publications Top Notes
π Outlier Suppression+: Accurate Quantization of Large Language Models by Equivalent and Optimal Shifting and Scaling
π₯ Authors: X. Wei, Y. Zhang, Y. Li, X. Zhang, R. Gong, J. Guo, X. Liu
π Conference: EMNLP (Empirical Methods in Natural Language Processing), 2023
π Citations: 144
π Focus: π’ Quantization | π‘ LLM Efficiency | π§ NLP
π Coarse-to-Fine Deep Video Coding with Hyperprior-Guided Mode Prediction
π₯ Authors: Z. Hu, G. Lu, J. Guo, S. Liu, W. Jiang, D. Xu
π Conference: CVPR (IEEE/CVF Conference on Computer Vision and Pattern Recognition), 2022
π Citations: 117
π Focus: π₯ Video Coding | π§ Deep Learning | π¦ Compression
π Multi-Dimensional Pruning: A Unified Framework for Model Compression
π₯ Authors: J. Guo, W. Ouyang, D. Xu
π Conference: CVPR (IEEE/CVF), 2020
π Citations: 106
π Focus: βοΈ Model Pruning | π Compression | π€ Efficiency
π Unsupervised Learning of Accurate Siamese Tracking
π₯ Authors: Q. Shen, L. Qiao, J. Guo, P. Li, X. Li, B. Li, W. Feng, W. Gan, W. Wu, W. Ouyang
π Conference: CVPR, 2022
π Citations: 83
π Focus: π§ Object Tracking | π§ Siamese Networks | π Unsupervised Learning
π Model Compression Using Progressive Channel Pruning
π₯ Authors: J. Guo, W. Zhang, W. Ouyang, D. Xu
π Journal: IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2020
π Citations: 78
π Focus: π¦ Channel Pruning | π Model Optimization | π¬ Vision
π Transformer3D-Det: Improving 3D Object Detection by Vote Refinement
π₯ Authors: L. Zhao, J. Guo, D. Xu, L. Sheng
π Journal: IEEE T-CSVT, 2021
π Citations: 70
π Focus: π¦ 3D Detection | π€ Transformers | π‘ Robotics
π Channel Pruning Guided by Classification Loss and Feature Importance
π₯ Authors: J. Guo, W. Ouyang, D. Xu
π Conference: AAAI Conference on Artificial Intelligence, 2020
π Citations: 62
π Focus: βοΈ Channel Pruning | π― Classification | βοΈ Network Efficiency
π JointPruning: Pruning Networks Along Multiple Dimensions for Efficient Point Cloud Processing
π₯ Authors: J. Guo, J. Liu, D. Xu
π Journal: IEEE T-CSVT, 2021
π Citations: 44
π Focus: π 3D Point Cloud | βοΈ Pruning | π€ Deep Learning
π Automatic Loss Function Search for Adversarial Unsupervised Domain Adaptation
π₯ Authors: Z. Mei, P. Ye, H. Ye, B. Li, J. Guo, T. Chen, W. Ouyang
π Journal: IEEE T-CSVT, 2023
π Citations: 34
π Focus: π Domain Adaptation | βοΈ Adversarial Learning | π§ͺ AutoML
π Annealing-Based Label-Transfer Learning for Open World Object Detection
π₯ Authors: Y. Ma, H. Li, Z. Zhang, J. Guo, S. Zhang, R. Gong, X. Liu
π Conference: CVPR, 2023
π Citations: 33
π Focus: π Transfer Learning | π Open-World AI | π― Detection
π SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
π₯ Authors: Z. Ying, A. Liu, S. Liang, L. Huang, J. Guo, W. Zhou, X. Liu, D. Tao
π Preprint: arXiv, 2024
π Citations: 32
π Focus: π‘οΈ Safety | π Evaluation | π€ LLMs
π CBANet: Toward Complexity and Bitrate Adaptive Deep Image Compression Using a Single Network
π₯ Authors: J. Guo, D. Xu, G. Lu
π Journal: IEEE Transactions on Image Processing (T-IP), 2023
π Citations: 32
π Focus: π· Image Compression | βοΈ Adaptive AI | π Model Efficiency