C
Scholar

Chuanguang Yang

Google Scholar ID: gYyDQqAAAAAJ
Institute of Computing Technology, Chinese Academy of Sciences
Failed to load scholar profile
Citations & Impact
All-time
Citations
0
 
H-index
0
 
i10-index
0
 
Publications
0
 
Co-authors
0
 
Publications
0 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Publications: NeurIPS-2025, ACM MM-2025, Scientific Data (on Traditional Chinese Medicinal Plant Dataset), ICCV-2025, SIGKDD-2025, The Innovation (an amazing review about Decision Intelligence), ICML-2025 (two papers), CVPR-2025, AAAI-2025 (three papers, two oral), ACM MM-2024 (oral), ICML-2024, CVPR-2024, AAAI-2024, ICCV-2023, TPAMI-2023, the first chapter of the book 《Advancements in Knowledge Distillation: Towards New Horizons of Intelligent Systems》by Springer Nature, ECCV-2022, TNNLS-2022, CVPR-2022, AAAI-2022 (two papers), IJCAI-2021, AAAI-2020. Awards: First prize in the 'Scientific and Technological Progress Award' (Technical Invention Category) of the 2025 China Institute of Command and Control Science and Technology Award. Invited Talks: CCF Outstanding Doctoral Dissertation Forum (2025), Microsoft Bing (2022), MSRA (2022), Session Chair of ICME-2022 Oral 36 Semantic Segmentation IV, Gaoling School of Artificial Intelligence, Renmin University of China (2022), Horizon Robotics (2022), AI Drive and Paper weekly (2021), SFFAI (2020).
Research Experience
  • Assistant Professor/Researcher: Domain-Oriented Intelligent System Research Center, Institute of Computing Technology, Chinese Academy of Sciences (2023.7~now).
Education
  • Ph.D. degree: Institute of Computing Technology, Chinese Academy of Sciences (2018.9~2023.6), supervised by Prof. Zhulin An and Prof. Yongjun Xu.
Background
  • Research Interests: Knowledge distillation for visual recognition models (e.g., image classification, object detection, semantic segmentation), visual generative models (e.g., diffusion), and multi-modal models (e.g., CLIP); Prompt learning for applying multi-modal large models to downstream visual recognition tasks; Image generation and editing based on Stable Diffusion; Other model compression techniques, including but not limited to efficient network architecture design, pruning, quantization, and dynamic inference.
Miscellany
  • Recruitment: The research group has 1~2 master's positions and 1 doctoral position available each year. Please pay attention to the summer camp, recommendation examination in July, and the entrance examination in March at the Institute of Computing Technology. Internship: There are 1~2 intern positions available, which can be either online or offline. If interested, please contact via email.
Co-authors
0 total
Co-authors: 0 (list not available)