Scholar
Jilan Xu
Google Scholar ID: mf2U64IAAAAJ
Fudan University
Computer Vision
Multimodal
Medical Image Analysis
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,574
H-index
16
i10-index
20
Publications
20
Co-authors
10
list available
Contact
Email
jilanxu18@fudan.edu.cn
Twitter
Open ↗
GitHub
Open ↗
Publications
18 items
Vision-Language Model Based Multi-Expert Fusion for CT Image Classification
2026
Cited
0
Clinical Priors Guided Lung Disease Detection in 3D CT Scans
2026
Cited
0
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams
2026
Cited
0
Scaling Audio-Text Retrieval with Multimodal Large Language Models
2026
Cited
0
EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
2025
Cited
0
EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
2025
Cited
0
Advancing Lung Disease Diagnosis in 3D CT Scans
2025
Cited
0
Multi-Source COVID-19 Detection via Variance Risk Extrapolation
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
- [09/2025] Three papers EgoThinker, AOR, EgoExoBench accepted to NeurIPS 2025
- [09/2025] One paper VinCi accepted to IMWUT 2025
- [09/2025] Ranked 1st in (1) Fair Disease Challenge and (2) Multi-Source COVID19 Detection Challenge @ ICCV 2025
- [07/2025] One paper Streamformer accepted to ICCV 2025 as an Oral paper
- [03/2025] EgoExoLearn won EgoVis 2023/2024 Distinguished Paper Award
- [01/2025] Three Papers EgoExo-Gen, EgoVideo, CGBench accepted to ICLR 2025
- [01/2025] Invited to give a talk on joint egocentric-exocentric video understanding at TechBeat
- [05/2024] Our CVPR papers Egoinstructor and EgoExoLearn accepted to 1st LPVL Workshop @ CVPR 2024
Research Experience
- Postdoctoral researcher at the Visual Geometry Group (VGG), University of Oxford
- Closely collaborates with Professor Weidi Xie at Shanghai Jiao Tong University
Education
- Ph.D. from Fudan University, advised by Professor Yuejie Zhang
- Postdoctoral researcher at the Visual Geometry Group (VGG), University of Oxford, advised by Professor Andrew Zisserman
Background
- Research Interests: Multimodal video understanding, visual representation learning, and medical image analysis
- Aspiration: To contribute to building medical AI agents that can heal the world and make it a better place for all humankind
Miscellany
- Contact: jilanxu18 at fudan dot edu dot cn
- Social Media: Google Scholar, Twitter, GitHub, Zhihu
Co-authors
10 total
Guo Chen
Nanjing University
Yu Qiao
Professor of Shanghai AI Laboratory; Shenzhen Institutes of Advanced Technology, CAS
Yifei Huang
The University of Tokyo
Junlin Hou
HKUST | Fudan University
Yi Wang
Shanghai AI Laboratory
Baoqi Pei
Zhejiang University
Kunchang Li
ByteDance Seed
Weidi Xie
Shanghai Jiao Tong University | VGG, University of Oxford
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up