Gao, Ruiyuan | 高瑞元
Ph.D in CSE of CUHK.
CUHK, Sha Tin, N.T.
Hong Kong, China
I am PhD candidate at CURE lab of CUHK. My supervisor is Prof. Qiang Xu.
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.
I am looking for jobs starting from Fall, 2025. Please do not hesitate to contact me through email!
Email: rygao.me [at] gmail.com
News
Dec 7, 2024 | We release all the checkpoints for MagicDrive and the final checkpoint for MagicDriveDiT. Enjoy the open-source! |
---|---|
Oct 29, 2024 | Three papers (Non-Cross Diffusion, TrackDiffusion, CODA-LM) are accepted to WACV 2025! |
Jun 21, 2024 | MagicDrive supports Pangu Large Model and appears at HDC2024! [More Details] |
Jun 1, 2024 | Based on MagicDrive and CODA-LM, we hold the “Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving” workshop (W-CODA2024) @ECCV24. Paper submission starts now, and challenge submission will start soon. Stay tuned! |
May 6, 2024 | 🎉 I will attend ICLR 24 at Vienna, Austria from May 7-11 2024. Check out MagicDrive@ICLR24 and hope see you there! |
Talks
Sep 11, 2024 | “3D Geometry in Data Synthesis for Autonomous Driving”, Li Auto Inc. |
---|---|
Jul 1, 2024 | "3D Geometry in Data Synthesis for Autonomous Driving", Autonomous Intelligence Lab, Westlake University. [More Details] |
Jan 18, 2024 | “MagicDrive - 基于3D几何控制的自动驾驶街景数据生成”, TechBeat, [online] |
Autonomous Driving
(*) denotes equal contribution.- ICLRMagicDrive: Street View Generation with Diverse 3D Geometry ControlIn International Conference on Learning Representations (ICLR) 2024
- TNNLSBoost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L_1 LossIEEE Transactions on Neural Networks and Learning Systems 2020
Generative Models
(*) denotes equal contribution.Robustness and AI Safety
(*) denotes equal contribution.- 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