Jianyuan
≡
profile photo

Jianyuan Guo (郭健元)

I am an Assistant Professor at the Department of Computer Science, City University of Hong Kong (CityUHK). I obtained the PhD from The University of Sydney, supervised by Prof. Chang Xu. I obtained the B.S. and M.S. from Peking University supervised by Prof. Chao Zhang. My main research interest lies in machine perception algorithms and their related applications, including neural network innovation for vision and natural language processing (LLMs/LVMs), signal processing in multimedia, multimodal understanding, edge computing, model compression, embodied AI, agent.

🔥Opening: I welcome applications from self-motivated PhD/Mphil students and interns who are passionate about efficient machine learning, multimodal models, LVM/LLM, WM/WAM, agentic FM. Feel free to send me an email with your CV, transcript, and a short research statement.

Email  /  Google Scholar  /  Github  /  DBLP

News

  • 06/2026, We release the survey of Harness Design.

  • 05/2026, We release the Autonomous Research System (paper).

  • 05/2025, Serve as AC for NeurIPS 2025.

  • 05/2025, 1 paper is accepted by IJCV.

  • 01/2025, Serve as AC for ICLR 2025.

  • 05/2024, 2 papers are accepted by ICML 2024.

  • 02/2024, Great honor to join the AAAI Student Committee.

  • 02/2024, We release the code of Data efficient Large Vision Model (DeLVM).

  • 10/2023, 4 papers are accepted by NeurIPS 2023.

  • 03/2022, 5 papers are accepted by CVPR 2022.

  • 09/2022, 4 papers are accepted by NeurIPS 2022.

    • Selected Publications

  • Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities.
    Zhiwei Hao, Jianyuan Guo, Li Shen, Yong Luo, Han Hu, Guoxia Wang, Dianhai Yu, Yonggang Wen, Dacheng Tao
    IEEE T-PAMI 2026 | paper

  • Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models.
    Chengcheng Wang*, Jianyuan Guo*, Hongguang Li*, Yuchuan Tian, Ying Nie, Chang Xu, Kai Han
    ICML 2026 | paper | code

  • KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs.
    Baiyang Song*, Jun Peng*, Yuxin Zhang, Guangyao Chen, Feidiao Yang, Jianyuan Guo
    AAAI 2026 | paper | code

  • Toward Effective Knowledge Distillation: Navigating Beyond Small-data Pitfall.
    Zhiwei Hao, Jianyuan Guo, Kai Han, Han Hu, Chang Xu, Yunhe Wang
    IEEE T-PAMI 2025 | paper

  • Bridging Sign and Spoken Languages:Pseudo Gloss Generation for Sign Language Translation.
    Jianyuan Guo, Peike Li, Trevor Cohn
    NeurIPS 2025 | paper

  • ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning.
    Zhiwei Hao, Jianyuan Guo, Shen Li, Yong Luo, Han Hu, Yonggang Wen
    IJCV 2025 | paper | code

  • Data-efficient Large Vision Models through Sequential Autoregression.
    Zhiwei Hao*, Jianyuan Guo*, Chengcheng Wang*, Yehui Tang, Han Wu, Han Hu, Kai Han, Chang Xu
    ICML 2024 | paper | code

  • GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer.
    Ding Jia*, Jianyuan Guo*, Kai Han, Han Wu, Chao Zhang, Chang Xu, Xinghao Chen
    ICML 2024 | paper | code

  • PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation.
    Zhiwei, Hao, Zhongyu Xiao, Yong Luo, Jianyuan Guo†, Jing Wang, Li Shen, Han Hu
    ACM MM 2024 | paper

  • Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning.
    Shibo Jie, Yehui Tang, Jianyuan Guo, Zhi-Hong Deng, Kai Han, Yunhe Wang
    ECCV 2024 | paper

  • Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale.
    Zhiwei Hao*, Jianyuan Guo*, Kai Han, Han Hu, Chang Xu, Yunhe Wang
    NeurIPS 2023 | paper | code

  • One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation.
    Zhiwei Hao, Jianyuan Guo, Kai Han, Yehui Tang, Han Hu, Yunhe Wang, Chang Xu
    NeurIPS 2023 | paper | code

  • VanillaNet: the Power of Minimalism in Deep Learning.
    Hanting Chen, Yunhe Wang, Jianyuan Guo, Dacheng Tao
    NeurIPS 2023 | paper | code

  • Hierarchical relational learning for few-shot knowledge graph completion.
    Han Wu, Jie Yin, Bala Rajaratnam, Jianyuan Guo
    ICLR 2023 | paper | code

  • Hire-MLP: Vision MLP via Hierarchical Rearrangement.
    Jianyuan Guo*, Yehui Tang*, Kai Han, Xinghao Chen, Han Wu, Chao Xu, Chang Xu, Yunhe Wang
    CVPR 2022 | paper | code

  • CMT: Convolutional Neural Networks Meet Vision Transformers.
    Jianyuan Guo, Kai Han, Han Wu, Chang Xu, Yehui Tang, Chunjing Xu, Yunhe Wang
    CVPR 2022 | paper | code

  • An Image Patch is a Wave: Quantum Inspired Vision MLP (WaveMLP).
    Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, Yunhe Wang
    CVPR 2022 | paper | code

  • Brain-inspired Multilayer Perceptron with Spiking Neurons.
    Wenshuo Li, Hanting Chen, Jianyuan Guo, Ziyang Zhang, Yunhe Wang
    CVPR 2022 | paper

  • Learning efficient vision transformers via fine-grained manifold distillation.
    Zhiwei Hao, Jianyuan Guo, Ding Jia, Kai Han, Yehui Tang, Chao Zhang, Han Hu, Yunhe Wang
    NeurIPS 2022 | paper

  • A Survey on Vision Transformer
    Kai Han, Yunhe Wang, Hanting Chen, Xinghao Chen, Jianyuan Guo, Zhenhua Liu, Yehui Tang, An Xiao, Chunjing Xu, Yixing Xu, Zhaohui Yang, Yiman Zhang, Dacheng Tao
    IEEE T-PAMI 2022 | paper

  • Positive-Unlabeled Data Purification in the Wild for Object Detection.
    Jianyuan Guo, Kai Han, Han Wu, Chao Zhang, Xinghao Chen, Chunjing Xu, Chang Xu, Yunhe Wang
    CVPR 2021 | paper

  • Distilling object detectors via decoupled features.
    Jianyuan Guo, Kai Han, Yunhe Wang, Han Wu, Xinghao Chen, Chunjing Xu, Chang Xu
    CVPR 2021 | paper | code

  • Transformer in Transformer.
    Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, Yunhe Wang
    NeurIPS 2021 | paper | code

  • OCNet: Object context for semantic segmentation
    Yuan Yuhui, Lang Huang, Jianyuan Guo, Chao Zhang, Xilin Chen, Jingdong Wang
    IJCV 2021 | paper

  • Hit-detector: Hierarchical trinity architecture search for object detection.
    Jianyuan Guo, Kai Han, Yunhe Wang, Chao Zhang, Zhaohui Yang, Han Wu, Xinghao Chen, Chang Xu
    CVPR 2020 | paper | code

  • Ghostnet: More features from cheap operations.
    Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, Chang Xu
    CVPR 2020 | paper | code

  • Beyond human parts: Dual part-aligned representations for person re-identification.
    Jianyuan Guo, Yuhui Yuan, Lang Huang, Chao Zhang, Jin-Ge Yao, Kai Han
    ICCV 2019 | paper | code

  • Attribute-aware attention model for fine-grained representation learning.
    Kai Han*, Jianyuan Guo*, Chao Zhang, Mingjian Zhu
    ACM MM 2018 | paper | code

    • Services

  • Student member in the AAAI Student Committee.

  • Conference Area Chair of ICLR, NeurIPS, AAAI.

  • Conference Reviewers of CVPR, ICCV, ECCV, ICLR, ICML, AAAI, NeurIPS, etc.

  • Journal Reviewers of TPAMI, IJCV, TIP, Pattern Recognition, Neurocomputing, TMLR, etc.

    • Teaching

  • CityUHK CS5494, Topics in Generative AI. Sem A.

  • CityUHK CS6487, Topics in Machine Learning. Sem B.

  • CityUHK CS5491, Artificial Intelligence. Sem B.

    • Selected Awards

  • 2026, Commendation, CORE Award for the Australasian Distinguished Dissertation

  • 2022, Google PhD Fellowship

  • 2020, Excellent Graduate, Peking University.

    • This website is based on the source code shared by Dr. Yunhe Wang. Thanks.