CUHK, Sha Tin, N.T.
Hong Kong, China
Before joining CUHK, I worked with Prof.Hailong YANG and Prof.Xianglong LIU at Beihang University, Beijing, and received a B.E. degree in computer science and technology from Shenyuan Honors College in 2020.
My current research interests span data generation, including generative models and synthetic data for perception tasks; and trustworthy AI, including adversarial attack/defence and AI privacy.
|Jul 14, 2023||One paper DiffGuard is accepted to ICCV 2023!|
|Dec 5, 2022||I join Huawei Noah’s Ark Lab as a Research Intern at Hong Kong, China.|
|Jul 4, 2022||Two paper MOODCat and DeciWatch is accepted to ECCV 2022!|
|Mar 10, 2022||I join Sensetime as a Research Intern of Digital Twin at Beijing, China.|
|Jan 21, 2022||One paper is accepted to ICLR 2022!|
Selected Publications(*) denotes equal contribution. See more at full list.
- arXivMagicDrive: Street View Generation with Diverse 3D Geometry ControlarXiv preprint arXiv:2310.02601 2023
- ICCVDiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion ModelsIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2023
- ECCVOut-of-Distribution Detection with Semantic Mismatch Under MaskingIn European Conference on Computer Vision 2022
- NDSSWhat You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic ContradictionIn Network and Distributed System Security Symposium (NDSS) 2022
- CCGridPriPro: Towards Effective Privacy Protection on Edge-Cloud System running DNN InferenceIn 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid) 2021
- TCYBModuleNet: Knowledge-Inherited Neural Architecture Search.IEEE transactions on cybernetics 2021