Research Directions: Energy-efficient embodied AI theory with physical scene and system hardware embedding (Physics and Hardware Embodied AI), primarily for edge devices and unmanned terminals. This includes 2D and 3D multi-modal embodied environment perception, understanding, and reasoning, human-centric embodied generation and reconstruction, and their low-power, high-robustness exploration in autonomous systems (e.g., robots, drones).

Key Research Areas in Deep Learning:

Hardware-software co-design and optimisation of embodied foundation models (AI Infra)

Brain-inspired resource-efficient AGI

Efficient inference and deployment design for edge intelligence

Group Goals: The group aims to address key technical challenges in national and industrial development, propose original AI solutions from 0 to 1, and train students in both theoretical and practical AI, with results published in top AI/CV journals/conferences (e.g., IEEE T-PAMI, IJCV, CVPR, ICCV, NeurIPS) or open-source communities (e.g., GitHub, HuggingFace). Previous research results have been adopted by leading Chinese companies (ByteDance, Tencent, Huawei, Xiaomi). Most graduates have joined these companies or pursued further studies at top-30 global universities (Cambridge, Duke, etc.).

Admissions: The group welcomes Master’s and PhD applicants with strong research interest. Priority is given to candidates with publications/submissions in the above journals/conferences, or strong programming/mathematical background and dedication to AI research. PhDs are jointly recruited with the National School of Artificial Intelligence (Shanghai Creative Intelligence Institute, application portal: Embodied AI and AI Systems direction) and Shanghai AI Laboratory. Outstanding candidates must pass interviews at both the partner institution and Fudan. Fudan Summer Camp 2025 application portal: College of Future Information Technology – Intelligent Information Processing and Systems direction.

Undergraduate Internships: Junior and senior undergraduates aspiring to future graduate study or research in edge intelligence are welcome. Applicants should commit approximately 70% of their time outside coursework to research. The lab will assist with recommendations to top international groups for further study. Postdoctoral researchers are also recruited year-round. For more information: https://eetchen.github.io/

PhD Recruitment (Autumn/Winter 2025): Joint recruitment through Shanghai Creative Intelligence Institute. Autumn camp registration open: https://mp.weixin.qq.com/s/dArOa_a3tmAOGgQTkxOihQ. Interested applicants may register and select the Embodied Intelligence direction.

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), Associate Editor, 2025–present

Shanghai Computer Society Computer Vision Specialised Committee, Deputy Secretary-General

Shanghai Image and Graphics Society, Board Member

Visual Big Data Specialised Committee of China Society of Image and Graphics, Committee Member

Youth Working Committee of China Society of Image and Graphics, Executive Committee Member

Multimedia Specialised Committee of China Computer Federation, Executive Committee Member

Industrial IoT Specialised Committee of Chinese Association of Automation, Executive Committee Member

IEEE Senior Member

VALSE (Vision and Learning Seminar), SAC

Journal of Artificial Intelligence and Systems, Editorial Board Member, 2019–2021

Mathematical Problems in Engineering, Guest Editor, 2015

ICSP 2016, Session Chair

Stanford University Top 2% of Scientists Worldwide (Single-Year Impact), 2025

International Joint Conference on Artificial Intelligence (IJCAI), Distinguished Paper Award, 2025

AI2000 List, 2023

Dean’s Award, School of Information Science and Technology, Fudan University, 2021

Shanghai Distinguished Expert (Special Appointment), 2020

National Young Distinguished Expert (Special Appointment), 2018

Special Outstanding Contribution Award for Autonomous Driving, Agency for Science, Technology and Research (A*STAR), Singapore, 2016

RIE2020 Research Innovation Contribution Award, Agency for Science, Technology and Research (A*STAR), Singapore, 2014

IEEE International Conference on Image Processing (ICIP) Conference Attendance Grant, 2011

Dec. 2023–present: Professor, Doctoral Supervisor, School of Information Science and Technology, Fudan University

Mar. 2019–Nov. 2023: Young Researcher, Doctoral Supervisor, School of Information Science and Technology, Fudan University

Aug. 2017–Feb. 2019: Senior Researcher, Huawei Singapore Central Research Institute

Apr. 2017–Jul. 2017: Researcher II, Institute for Infocomm Research (I²R), Singapore

May 2013–Mar. 2017: Researcher I, Institute for Infocomm Research (I²R), Singapore

Jan. 2013–Apr. 2013: Associate Researcher, NTU Intelligent Robotics Laboratory

Aug. 2008–Sept. 2013: Ph.D., Nanyang Technological University, Singapore

Sept. 2006–Jul. 2008: M.Eng., Zhejiang University

Sept. 2002–Jul. 2006: B.Eng., Shandong University

Image Processing and Machine Vision, Year 3 (Spring Semester)

Computer Vision, Year 1 (Spring Semester)

Pattern Recognition, Year 1 (Autumn Semester)

Over the past five years, the lab has published more than 150 papers in CCF Class A and CAS Tier 1 AI venues such as IEEE T-PAMI / T-IP / T-GRS / T-MM / CVPR / NeurIPS / ACMMM. Parts of the work have been adopted by companies including Huawei, ZTE and Xiaomi. The detailed paper list is provided below:

A List of FULL Publications, please see:

https://scholar.google.com.sg/citations?hl=en&user=w3OoFL0AAAAJ&view_op=list_works&sortby=pubdate

Y. Liao, H. Zhu, Y. Zhang, C. Ye, J. Fan, T. Chen, "Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining," IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022.

H. Ye, B. Zhang, T. Chen, "Performance-aware Approximation of Global Channel Pruning for Multitask CNNs," IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023.

C. Ye, H. Zhu, B. Zhang, T. Chen, "A Closer Look at Few-shot 3D Point Cloud Classification," to appear, International Journal of Computer Vision (IJCV), 2023.

P. Ye, B. Li, Y. Li, T. Chen, et al., "Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation," International Journal of Computer Vision (IJCV), 2022.

T. Chen, S. Lu, J. Fan, "S-CNN: Subcategory-aware convolutional networks for object detection," IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 40(10):2522-2528, 2018.