Biography

I am an Associate Professor of the Computational and Photogrammetric Vision Team (Captain), School of Artificial Intelligence, Wuhan University. Prior to that, I was a senior research scientist at Tencent AI Lab. I received Ph.D. degree in Electronic Engineering Department of City University of Hong Kong, during which I visited Center for Cognition, Vision, and Learning (CCVL) of UCLA. Before that, I obtained B.S. and M.S. degrees both from Huazhong University of Science and Technology.

I developed several (Statistical) Machine Learning algorithms and have applied them to Computer Vision with Prof. Alan Yuille, to Complex Network with Prof. Guanrong Chen, to Bioinformatics with Dr. Rosa Chan and Dr. Panpan Hou, with products delivered at Tencent and Pinduoduo.

My current research interests include Multi-Modality & Multi-Task AI, with its efficiency in training & inference, and its applications mainly to Computer Vision.

• Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation.
  Guopeng Li, Qiang Wang, Ke Yan, Shouhong Ding, Yuan Gao^, and Gui-Song Xia^. (^ indicates corresponding authors)
  IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

  PDF BibTex arXiv

• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient.
  Yuan Gao*, Zujing Liu*, Weizhong Zhang*, Bo Du, and Gui-Song Xia. (* indicates equal contributions)
  The Annual Meeting of the Association for Computational Linguistics (ACL), 2025.

  PDF BibTex Code arXiv Poster

• DMTG: One-Shot Differentiable Multi-Task Grouping.
  Yuan Gao, Shuguo Jiang, Moran Li, Jin-Gang Yu, and Gui-Song Xia.
  International Conference on Machine Learning (ICML), 2024.

  PDF BibTex Code arXiv Poster

• Anchor-based Robust Finetuning of Vision-Language Models.
  Jinwei Han, Zhiwen Lin, Zhongyisun Sun, Yingguo Gao, Ke Yan, Shouhong Ding, Yuan Gao^, and Gui-Song Xia^. (^ indicates corresponding authors)
  IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

  PDF BibTex arXiv

• Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost.
  Yuan Gao, Weizhong Zhang, Wenhan Luo, Lin Ma, Jin-Gang Yu, Gui-Song Xia, and Jiayi Ma.
  International Conference on Learning Representations (ICLR), 2024.

  PDF BibTex Code arXiv Poster

• Locality Preserving Refinement for Shape Matching with Functional Maps.
  Yifan Xia, Yifan Lu, Yuan Gao^, Jiayi Ma^. (^ indicates corresponding authors)
  AAAI Conference on Artificial Intelligence (AAAI), 2024.

  PDF BibTex Code

• Exploiting Learnable Joint Groups for Hand Pose Estimation.
  Moran Li*, Yuan Gao*, and Nong Sang. (* indicates equal contributions)
  AAAI Conference on Artificial Intelligence (AAAI), 2021.

  PDF BibTex Code arXiv

• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning.
  Yuan Gao*, Haoping Bai*, Zequn Jie, Jiayi Ma, Kui Jia, and Wei Liu. (* indicates equal contributions)
  IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

  PDF BibTex Code Supp. Materials arXiv Poster

• Estimation of 3D Category-Specific Object Structure: Symmetry, Manhattan and/or Multiple Images.
  Yuan Gao^, and Alan L. Yuille. (^ indicates corresponding author)
  International Journal of Computer Vision (IJCV), 2019.

  PDF BibTex Supp. Materials

• NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction.
  Yuan Gao, Jiayi Ma, Mingbo Zhao, Wei Liu, and Alan L. Yuille.
  IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

  PDF BibTex Code Supp. Materials arXiv Poster

• Feature-guided Gaussian Mixture Model for Image Matching.
  Jiayi Ma, Xingyu Jiang, Junjun Jiang, and Yuan Gao^. (^ indicates corresponding author)
  Pattern Recognition, vol.92, pp.231-245, 2019.

  PDF BibTex

• Inactivation of KCNQ1 potassium channels reveals dynamic coupling between voltage sensing and pore opening.
  Panpan Hou, Jodene Eldstrom, Jingyi Shi, Ling Zhong, Kelli McFarland, Yuan Gao, David Fedida, and Jianmin Cui.
  Nature Communications, vol.8, article no.1730, 2017.

  PDF BibTex

• Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation from Single and Multiple Images.
  Yuan Gao, and Alan L. Yuille.
  IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

  PDF BibTex Supp. Materials arXiv

• Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples.
  Yuan Gao, Jiayi Ma, and Alan L. Yuille.
  IEEE Transactions on Image Processing (TIP), vol.26, no.5, pp.1-16, 2017. (ESI Highly Cited Paper)

  PDF BibTex Code arXiv

• Symmetric Non-Rigid Structure from Motion for Category-Specific Object Structure Estimation.
  Yuan Gao, and Alan L. Yuille.
  European Conference on Computer Vision (ECCV), 408-424, 2016.

  PDF BibTex Supp. Materials arXiv

• Computational classification of different wild-type zebrafish strains based on their variation in light-induced locomotor response.
  Yuan Gao, Gaonan Zhang, Beth Jelfs, Yuk Fai Leung, Rosa H.M. Chan, et al.
  Computers in Biology and Medicine, vol.69, pp.1–9, 2016.

  PDF BibTex

• Naming Game on Networks: Let Everyone be Both Speaker and Hearer.
  Yuan Gao, Guanrong Chen, and Rosa H. M. Chan.
  Scientific Reports, vol.4, no.6149, 2014.

  PDF BibTex Supp. Materials arXiv

• A high-throughput zebrafish screening method for visual mutants by light-induced locomotor response.
  Yuan Gao, Rosa H. M. Chan, Tommy W. S. Chow, Liyun Zhang, Sylvia Bonilla, Yuk Fai Leung, et al.
  IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), vol.11, no.4, pp.693-701, 2014.

  PDF BibTex Supp. Materials