Yanwei Fu is a tenure-track professor  at the School of Data Science, Fudan University, Shanghai China.

He is  Professor of Eastern Scholar, Shanghai (上海高校特聘教授 – 东方学者), 1000 young scholar (青千)，and ARC DECRA fellow.

Research interests

He is interested in the following ML/CV topics (with the corresponding selected papers from my Project page):

1, Learning from small samples by exploring the Statistical sparsity

• Statistical Sparsity: Lasso-type ML methods
• One/Few-shot/Supervised learning by statistical methods

2, Learning based 3D/4D object/body Reconstruction and Robotic Grasping;

• 4D Object Mesh sequence reconstruction from videos/point clouds
• 6DoF Object Pose Estimation Robotic Grasping

3, AIGC, Foundation Models.

• AIGC for 3D models: Foundation to generated 3D pointcloud or meshes of objects
• Mind-Visualization: visualizing fMRI into images
• Foundation models for Image Manipulation and Editing
• RobotGPT: ChatGPT enabling the Robot Tasks

Please use the key words to search the corresponding papers from my Project Pages.

Homepage of interesting tasks: 1) Inpainting: zits++: https://ewrfcas.github.io/ZITS-PlusPlus/ CasMTR: https://ewrfcas.github.io/CasMTR/ ARCI: https://ewrfcas.github.io/ARCI/

2)Vision-Guided Robotic Grapsing: 2.1, we have used Large Language Model (LLM) to improve the performance of robotics: https://star-uu-wang.github.io/WALL-E/ 2.2, Our ICCV 23’s work in fancy controlling the robotics for pouring water: https://hetolin.github.io/PourIt/ 2.3, Our CVPR22, ICRA2022 works on vision guided robotic grasping in general. 6DoF category-level object localization https://hetolin.github.io/SAR-Net/ 2.4 sketch-guided robotic grasping https://hetolin.github.io/Skt_grasp/

Timeline

• Jan. 2015 – July 2016, postdoctoral researcher, Disney Research Pittsburgh with Dr. Leon Sigal
• Sep. 2011 – Nov. 2014 PhD in Computer Vision, Queen Mary University of London, with Prof. Tao Xiang (Tony) and Prof. Shaogang Gong (Sean)
• Sep. 2008 – Jun. 2011 Master in Computer Science, Nanjing University with Prof. Yanwen Guo.

Please donot contact me via my QMUL email address, which has been suspended.

关于本组招生：大数据学院科学硕士及直博生是统一招生（而不是分配给导师名额）。所以感兴趣我们组的话，可以直接去申请拿到学院的offer，再联系我即可。申请普博或者Oversea students想来我们组做summer intern的话，可以提前联系我。

大家有兴趣联系我们，可以email联系我或我们组博士后钱学林老师(xuelinq@163.com)。 2023年9月开始，因为最近人数比较多，我们组暂不收本科实习生（有兴趣报送本组读硕士、博士的本科生可以来）。 有兴趣做statistical sparsity的本科同学，可以直接联系孙鑫伟老师，我们可以一起合作。

另外，自2023年9月起，我们组轮转名额已满，暂不接收类脑院同学轮转。

Recent News

• 07/2023 1 IROS 2023 paper, and 7 ICCV 2023 papers accepted
• 06/2023 I will organize CVPR 2023 few-shot learning tutorial: https://fsl-fudan.github.io!
• 05/2023 Chengming Xu, Boyang Jiang, Yuqian Fu, and Qiang Sun passed their PhD Viva. Congratulations!
• 05/2023 One IEEE TPAMI paper accepted – ZITS++
• 01/2023 I will serve as ICML 2023 Area Chair. I guess it may be still challenging, as ML community always likes to make some experiments in exploring a better review process.
• 12/2022 One IEEE TPAMI and one TMLR paper accepted! The TPAMI one about identifying causal features in one-shot learning; TMLR one is about DINO features for MVS, which took the first place in tank and temples Leaderboard , during the past 6 months. We released their codes. This year, our group has 4 accepted IEEE TPAMI papers, 2 accepted TMLR paper.
• 12/2022 Yu Xie, and Pan Li passed their PhD Viva. Congratulations!
• 08/2022 I  will organize the tutorial “The Priors Guided Image Editing and Synthesis” with Prof. Shenghua Gao, Mr. Chenjie Cao, and Mr. Qiaole Dong in ACCV 2022, held in Macau SAR, China.
• 07/2022 We organize the 2nd Visual Intelligence Seminar on Few-shot Learning with Online videos
• 07/2022 Our MVSFormer has ranked as Top-1 (since May) on the leaderboard
• 07/2022 Two ACM MM2022 and Three ECCV2022 papers accepted.
• 06/2022 I am a Fellow member of BCS.
• 06/2022 I organized a CVPR 2022 tutorial of “Sparsity Learning in Neural Networks and Robust Statistical Analysis”, jointly with  Dr. Xinwei Sun, Prof. Yuan Yao, and Prof. Wotao Yin.
• 05/2022 Three IEEE TPAMI papers accepted.
• 03/2022 I am in the action editor list of Transactions on Machine Learning Research.
• 02/2022 Ten papers accepted to CVPR 2022
• 02/2022 Two papers accepted to ICRA 2022
• 01/2021 We organize the 1st Visual Intelligence Seminar on Few-shot Learning.

Media Interview

• 05/2023 https://m.thepaper.cn/newsDetail_forward_23279276 ````````