Wuyang LI

I am a Research Scientist (since Feb 2025) at the VITA (Visual Intelligence for Transportation) Lab at EPFL (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne). I feel extremely fortunate to work under the supervision of Prof. Alexandre Alahi. My research focuses on autonomous mobility and robotics, as well as developing innovative computer vision and machine learning solutions.

Before this, I worked as a Postdoctoral Researcher (2024–2025) at the Chinese University of Hong Kong (CUHK) and completed my PhD (2020–2023) at the City University of Hong Kong (CityUHK) with Early Graduation. During my PhD, I focused on visual perception in the context of autonomous driving, thoroughly addressing two-dimensional challenges posed by out-of-distribution data and domain shifts. I was also fortunate to have had the opportunity to work with Prof. Bo Han. I completed my undergraduate studies (2016–2020) at Tianjin University.

I am open to research collaborations. If you are interested in my previous work, please don't hesitate to contact me.

Email  /  CV  /  Google Scholar  /  Github

profile photo

πŸ’₯ News

  • [03-2025] 1 co-authored papers about LLM is accepted by TMI 2025! Thanks to all the co-authors!
  • [02-2025] 2 co-authored papers (FlexGS and TAO) are accepted by CVPR 2025! Thanks to all the co-authors!
  • [01-2025] 2 co-authored papers (InstantSplamp and PDH-Diffusion) are accepted by ICLR 2025! Thanks to all the co-authors!
  • [01-2025] 1 co-authored paper (Hide-In-Motion) is accpectd by ICRA 2025! Thanks to all the co-authors!
  • [12-2024] 2 co-authored papers (U-KAN and DPA) are accepted by AAAI 2025! Thanks to all the co-authors!
  • [12-2024] 1 co-authored paper on 3D GS watermarking has been accepted by ICASSP 2025!
  • [11-2024] 1 co-authored paper about MRI phenotype prediction foundation model is accepted by TMI 2024! Contracts to Zhibin!
  • [10-2024] I am selected as the Top Reviewer at NeurIPS 2024!
  • [09-2024] 1 paper about SAM for uncertainty modeling is accepted by NeurIPS 2024. Congrats to Chenxin!
  • [Milestone] From 08/2021 to 08/2024, my first-author works have been selected as ORAL at 4 CV conferences: CVPR, ICCV, ECCV, and AAAI!
  • [08-2024] Our work CLIFF is selected as ORAL in ECCV
  • [07-2024] We are organizing the first workshop on multi-modal medical foundation models at NeurIPS; Submission Link
  • [07-2024] 1 paper using diffusion to tackle the open-vocabulary issue from a probabilistic viewpoint is accepted by ECCV 2024
  • [06-2024] 6 papers are accepted by MICCAI 2024 , including the works related to:
    Video Generation, Efficient Gaussian Splatting, 3D Point Cloud Segmentation,
    Diffusion Model, and Brain Analysis.
  • [04-2024] Our work on metasurfaces and stereo vision has been selected as the Cover Paper in ACS Photonics!
  • [12-2023] I pass my PhD defense with Early Graduation!!
  • [08-2023] Our work SOMA is selected as ORAL in ICCV.
  • [07-2023] 2 papers are accepted by ICCV 2023.
  • [06-2023] Successfully secured seed funding for our startup team!
  • [05-2023] 1 paper is accepted by MICCAI 2023.
  • [04-2023] 1 paper is accepted by TNNLS 2023.
  • [03-2023] 1 paper is accepted by TMI 2023.
  • [02-2023] 1 paper is accepted by CVPR 2023.
  • [01-2023] 1 paper is accepted by TPAMI 2023.
  • [10-2022] 1 paper is accepted by TMM 2022.
  • [06-2022] Our work SIGMA appears on CVPR Best Paper Finalist [33/8161]!
  • [05-2022] 1 paper is accepted by MICCAI 2022 ( Early Accept, ORAL).
  • [03-2022] 2 papers are accepted by CVPR 2022 (one ORAL ).
  • [10-2021] Our work SCAN is accepted by AAAI 2022 ( ORAL ).

πŸ“‘ Selected Publication
VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection
ArXiv Preprint, 2025
Wuyang Li, Zhuy Yu, Alexandre Alahi
project page / paper / codes (coming)
Key Words: 3D Semantic Occupancy Prediction; Dense Object Detection
TL;DR: VoxDet address semantic occupancy prediction with an instance-centric formulation inspried by dense object detection, which uses a VoxNT trick freely transferring voxel-level class labels to instance-level offset labels.
CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection
European Conference on Computer Vision, ECCV, 2024, ORAL
Wuyang Li, Xinyu Liu, Jiayi Ma, Yixuan Yuan
paper / codes / video
Key Words: Open-Vocabulary Object Detection; Diffusion Model
TL;DR: A probabilistic pipeline modeling the subspace transfer among the object, image, and text subspaces with continual diffusion.
From Static to Dynamic Diagnostics: Boosting Medical Image Analysis via Motion-Informed Generative Videos
Medical Image Computing and Computer Assisted Intervention, , MICCAI, 2024
Wuyang Li, Xinyu Liu, Qiushi Yang, Yixuan Yuan
paper
Key Words: Medical Video Generation; Semi-Supervised Diagnosis
TL;DR: Enhancing the semi-supervised diganosis with generative medical videos, enabling the learning across image and video modalities jointly.
When 3D Partial Points Meets SAM: Tooth Point Cloud Segmentation with Sparse Labels
Medical Image Computing and Computer Assisted Intervention, , MICCAI, 2024
Yifan Liu, Wuyang Li, Cheng Wang, Hui Chen, Yixuan Yuan
paper
Key Words: SAM; 3D Point Cloud Segmentation; Severely Limited Label
TL;DR: Leveraging the SAM to address the severe label scarcity in 3D point cloud segmentation, enbaling good perfromance with only 0.1% label ratio.
Novel Scenes & Classes: Towards Adaptive Open-set Object Detection
IEEE International Conference on Computer Vision (ICCV), 2023, ORAL
Wuyang Li, Xiaoqing Guo, Yixuan Yuan
paper / codes
Key Words: Open-Set/ Domain Adaptive Object Detection
TL;DR: Formulating a real-world friendly setting with out-of-distribution and domain shift, and addressing with high-order subgraphs.
MRM: Masked Relation Modeling for Medical Image Pre-Training with Genetics
IEEE International Conference on Computer Vision (ICCV), 2023
Qiushi Yang, Wuyang Li, Paul Li, Yixuan Yuan
paper / codes
Key Words: Multimodal Pretraining; Masked Image Modeling
TL;DR: Observing the failure in MIM when the informative foreground is limited, and turning to masking relation to solve this issue.
Adjustment and Alignment for Unbiased Open Set Domain Adaptation
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Wuyang Li, Jie Liu, Bo Han, Yixuan Yuan
paper / codes/ video
Key Words: Open Set Domain Adaptation; Causal Theory
TL;DR: Driven by new observations, proposing a theoretically grounded method to tackle biased learning and cross-domain transfer with causality.
SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, ORAL, Best Paper Finalist
Wuyang Li, Xinyu Liu, Yixuan Yuan
paper / codes / ηŸ₯乎
Key Words: Domain Adaptive Object Detection; Graph Matching
TL;DR: Reformulating domain adaptation as a graph matching problem among fine-grained cross-domain feature points.
Towards Robust Adaptive Object Detection under Noisy Annotations
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Xinyu Liu, Wuyang Li, Qiushi Yang, Baopu Li, Yixuan Yuan
paper / codes
Key Words: Open Set Domain Adaptation; Noisy Label
TL;DR: Exploring a more practical setting with noisy annotations in DAOD and solving by measuring the latent transferability of object noise.
SCAN: Cross Domain Object Detection with Semantic Conditioned Adaptation
The Association for the Advance of Artificial Intelligence (AAAI), 2022, ORAL
Wuyang Li, Xinyu Liu, Xiwen Yao, Yixuan Yuan
paper / codes
Key Words: Open Set Domain Adaptation; Graph-based Learning
TL;DR: Discovering the key factor leading to the perforrmance drop in DAOD and addressing with cross-domain semantic-conditioned kernels.
Intervention & Interaction Federated Abnormality Detection with Noisy Clients
Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022, ORAL, Early Accept
Xinyu Liu, Wuyang Li, Yixuan Yuan
paper / codes
Key Words: Federated Learning; Noisy Label; Causal Theory
TL;DR: Studying the recognition bias in federated object detection under noisy annotations, and addressing the bias with a novel causal intervention.
SIGMA++: Improved Semantic-complete Graph Matching for Domain Adaptive Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, IF: 24.314
Wuyang Li, Xinyu Liu, Yixuan Yuan
paper / codes
Key Words: Domain Adaptive Object Detection; Hypergraph Matching
TL;DR: Improving pair-wise SIGMA with high-order hypergraph, thereby addressing the domain misalignment with group-level adaptation.
HTD: Heterogeneous Task Decoupling for Two-Stage Object Detection
IEEE Transactions on Image Processing (TIP), 2022, IF: 11.041
Wuyang Li, Zhen Chen, Baopu Li, Dingwen Zhang, Yixuan Yuan
paper / codes
Key Words: Generic Object Detection; Graph-based Learning
TL;DR: Discovering the heterogeneous feature demands between the classification and regression, and solving via task-decoupled designs.
Decoupled Unbiased Teacher for Source-Free Domain Adaptive Medical Object Detection
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
Xinyu Liu, Wuyang Li, Yixuan Yuan
paper / codes
Key Words: Source-free Domain Adaptive Object Detection; Causal Theory
TL;DR: Identifying the bias at the data, model and prediction levels in SFDA, and sovling with causal intervention.

πŸ“„ Other Publication

Image/Video Generative Models

  • Endora: Video Generation Models as Endoscopy Simulators
    Chenxin Li, Hengyu Liu, Yifan Liu, Brandom Feng, Wuyang Li, Xinyu Liu, Zhen Chen, Jing Shao, Yixuan Yuan
    Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024
  • DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image Segmentation
    Xinyu Liu, Wuyang Li, Yixuan Yuan
    Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024

Brain MRI Analysis

  • FM-APP: Foundation Model for Any Phenotype Prediction via fMRI to sMRI Knowledge Transfer
    Zhibin He, Wuyang Li, Yifan Liu, Xinyu Liu, Junwei Han, Tuo Zhang, Yixuan Yuan
    IEEE Transactions on Medical Imaging (TMI), 2024, Under Review
  • F2TNet: FMRI to T1w MRI Knowledge Transfer Network for Brain Multi-phenotype Prediction
    Zhibin He, Wuyang Li, Yu Jiang, Zhihao Peng, Pengyu Wang, Xiang Li, Tianming Liu, Junwei Han, et al.
    Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024
  • H2GM: A Hierarchical Hypergraph Matching Framework for Brain Landmark Alignment
    Zhibin He, Wuyang Li, Tuo Zhang, Yixuan Yuan
    Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023

LLM Agent

  • LLM-guided Decoupled Probabilistic Prompt for Continual Learning in Medical Image Diagnosis
    Yiwen Luo, Wuyang Li, Chen Cheng, Xiang Li, Tianming Liu, Yixuan Yuan
    IEEE Transactions on Medical Imaging (TMI), 2024, Under Revision

3D Vision

  • LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction
    Hengyu Liuβˆ—, Yifan Liuβˆ—, Chenxin Liβˆ—, Wuyang Li, Yixuan Yuan
    Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024
  • Stereo Vision Meta-Lens-Assisted Driving Vision
    Xiaoyuan Liu, Wuyang Li, Takeshi Yamaguchi, Zihan Geng, Takuo Tanaka, Din Ping Tsai, Mu Ku Chen
    ACS Photonics, 2024, Selected as Cover Paper
  • GRAB-Net: Graph-based Boundary-aware Network for Medical Point Cloud Segmentation
    Yifan Liu, Wuyang Li, Jie Liu, Hui Chen, Yixuan Yuan
    IEEE Transactions on Medical Imaging (TMI), 2023

Graph-based Learning

  • Medical Federated Learning with Joint Graph Purification for Noisy Label Learning
    Zhen Chen, Wuyang Li, Xiaohan Xing, Yixuan Yuan
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
  • SCAN++: Enhanced Semantic Conditioned Adaptation for Domain Adaptive Object Detection
    Wuyang Li, Xinyu Liu, Yixuan Yuan
    IEEE Transactions on Multimedia (TMM), 2022

Medical Imaging Analysis

  • U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation
    Chenxin Liβˆ—, Xinyu Liuβˆ—, Wuyang Liβˆ—, Cheng Wangβˆ—, Hengyu Liu, Yixuan Yuan (βˆ— Equal Contribution)
    ArXiv preprint arXiv:2406.02918, 2024
  • Joint polyp detection and segmentation with heterogeneous endoscopic data
    Wuyang Li, Chen Yang, Jie Liu, Xiaoqing Guo, Yixuan Yuan
    International Symposium on Biomedical Imaging (ISBI) Workshop, 2021

πŸ’‘ Service

Journals Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • International Journal of Computer Vision (IJCV)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Image Processing (TIP)
  • IEEE Transactions on Automation Science and Engineering (TASE)
  • Pattern Recognition (PR)

Conferences Reviewer

  • Conference on Neural Information Processing Systems (neurIPS), 2024
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 2024
  • IEEE International Conference on Computer Vision (ICCV), 2023
  • AAAI Conference on Artificial Intelligence (AAAI), 2023, 2024

πŸ… Selected Honors

  • [2023] Outstanding Academic Performance Award (OAPA), CityU
  • [2023] Research Tuition Scholarship (RTS), CityU
  • [2022] Outstanding Academic Performance Award (OAPA), CityU
  • [2022] Research Tuition Scholarship (RTS), CityU
  • [2018] National Scholarship (Top 2% student)
  • [2017] National Scholarship (Top 2% student)
  • [2017] Tianjin Mathematical Competition (Second Prize)
  • [2017-2020] Outstanding Student Scholarship (Top 10% student)

πŸŽ“ Education
Tianjin University (TJU), China

Sep. 2016 - Jun. 2020： Bachelor's degree of Communication Engineering.

GPA: 3.83/4.00, 91.3/100, Ranking 6/120
NUS (Suzhou) Research Institute (NUSRI), China

Sep. 2019 - Jun. 2020: Exchanging program of Electrical and Computer Engineering.

Supervisors: Prof. Zhiying Zhou

Complete the project: Towards Webpage-based Augmentation Reality (AR)
City University of Hong Kong (CityU), China

Sep. 2020 - Dec. 2023: Ph.D Study of Electrical Engineering.

Supervisors: Prof. Yixuan Yuan

πŸ‘₯ Leadership
Founder & Director, ScholaGO Education Technology Company Limited

To gain a deeper understanding of technology, I founded ScholaGO Education Technology Company Limited (ε­Έζ—…ι€šζ•™θ‚²η§‘ζŠ€ζœ‰ι™ε…¬εΈ) with four co-founders to develop an innovative educational product aimed at converting static knowledge into an immersive, interactive, multi-modal adventure. Our company is supported by HKSTP, HK Tech 300, and Alibaba Cloud. My ultimate goal is to develop valuable technologies and products to improve the national happiness index.

🎨 Personal Interests

  • Painting and Designing: I used to do sketch training with art candidates and have a a certain level of graphic design foundation. I have a strong interest in user needs analysis and product design.
  • I am looking for the opportunity to establish a start-up team and create some awesome high-tech products.

We steal this website from this guy